Upload folder using huggingface_hub
Browse files- README.md +173 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- checkpoint-2000/README.md +202 -0
- checkpoint-2000/adapter_config.json +34 -0
- checkpoint-2000/adapter_model.safetensors +3 -0
- checkpoint-2000/config.json +35 -0
- checkpoint-2000/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-2000/global_step2000/mp_rank_00_model_states.pt +3 -0
- checkpoint-2000/latest +1 -0
- checkpoint-2000/non_lora_trainables.bin +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/special_tokens_map.json +27 -0
- checkpoint-2000/tokenizer.model +3 -0
- checkpoint-2000/tokenizer_config.json +48 -0
- checkpoint-2000/trainer_state.json +0 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2000/zero_to_fp32.py +578 -0
- config.json +35 -0
- model_named_parameters.txt +743 -0
- non_lora_trainables.bin +3 -0
- trainer_state.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- finetuned
|
| 6 |
+
- multimodal
|
| 7 |
+
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
| 8 |
+
dataset: ./out
|
| 9 |
+
inference: false
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
These are weights for a version of `mistralai/Mixtral-8x7B-Instruct-v0.1` finetuned for multimodal applications.
|
| 13 |
+
|
| 14 |
+
### Modalities
|
| 15 |
+
|
| 16 |
+
* CLIPVisionModality (use `<image>` in text and provide `images`, encoded as 576 tokens)
|
| 17 |
+
|
| 18 |
+
### Usage
|
| 19 |
+
|
| 20 |
+
GitHub: https://github.com/sshh12/multi_token (includes training scripts and basic inference server)
|
| 21 |
+
|
| 22 |
+
### Dataset
|
| 23 |
+
|
| 24 |
+
./out (558128 examples)
|
| 25 |
+
|
| 26 |
+
```
|
| 27 |
+
{'id': '004539375', 'images': ['/data/llava_pretrain_data/images/00453/004539375.jpg'], 'messages': [{'content': 'Render a clear and concise summary of the photo.\n<image>', 'role': 'user'}, {'content': 'select luxury furniture 3 - inch gel memory foam mattress topper', 'role': 'assistant'}]}
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
### Training Device(s)
|
| 31 |
+
|
| 32 |
+
```
|
| 33 |
+
name, pci.bus_id, vbios_version
|
| 34 |
+
NVIDIA GeForce RTX 3090, 00000000:B3:00.0, 94.02.42.00.B4
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
### Model
|
| 39 |
+
|
| 40 |
+
```
|
| 41 |
+
MistralLMMForCausalLM.model =
|
| 42 |
+
|
| 43 |
+
PeftModelForCausalLM(
|
| 44 |
+
(base_model): LoraModel(
|
| 45 |
+
(model): MistralLMMForCausalLM(
|
| 46 |
+
(model): MistralLMMModel(
|
| 47 |
+
(embed_tokens): Embedding(32000, 4096)
|
| 48 |
+
(layers): ModuleList(
|
| 49 |
+
(0-31): 32 x MistralDecoderLayer(
|
| 50 |
+
(self_attn): MistralAttention(
|
| 51 |
+
(q_proj): lora.Linear(
|
| 52 |
+
(base_layer): Linear(in_features=4096, out_features=4096, bias=False)
|
| 53 |
+
(lora_dropout): ModuleDict(
|
| 54 |
+
(default): Dropout(p=0.05, inplace=False)
|
| 55 |
+
)
|
| 56 |
+
(lora_A): ModuleDict(
|
| 57 |
+
(default): Linear(in_features=4096, out_features=64, bias=False)
|
| 58 |
+
)
|
| 59 |
+
(lora_B): ModuleDict(
|
| 60 |
+
(default): Linear(in_features=64, out_features=4096, bias=False)
|
| 61 |
+
)
|
| 62 |
+
(lora_embedding_A): ParameterDict()
|
| 63 |
+
(lora_embedding_B): ParameterDict()
|
| 64 |
+
)
|
| 65 |
+
(k_proj): lora.Linear(
|
| 66 |
+
(base_layer): Linear(in_features=4096, out_features=1024, bias=False)
|
| 67 |
+
(lora_dropout): ModuleDict(
|
| 68 |
+
(default): Dropout(p=0.05, inplace=False)
|
| 69 |
+
)
|
| 70 |
+
(lora_A): ModuleDict(
|
| 71 |
+
(default): Linear(in_features=4096, out_features=64, bias=False)
|
| 72 |
+
)
|
| 73 |
+
(lora_B): ModuleDict(
|
| 74 |
+
(default): Linear(in_features=64, out_features=1024, bias=False)
|
| 75 |
+
)
|
| 76 |
+
(lora_embedding_A): ParameterDict()
|
| 77 |
+
(lora_embedding_B): ParameterDict()
|
| 78 |
+
)
|
| 79 |
+
(v_proj): lora.Linear(
|
| 80 |
+
(base_layer): Linear(in_features=4096, out_features=1024, bias=False)
|
| 81 |
+
(lora_dropout): ModuleDict(
|
| 82 |
+
(default): Dropout(p=0.05, inplace=False)
|
| 83 |
+
)
|
| 84 |
+
(lora_A): ModuleDict(
|
| 85 |
+
(default): Linear(in_features=4096, out_features=64, bias=False)
|
| 86 |
+
)
|
| 87 |
+
(lora_B): ModuleDict(
|
| 88 |
+
(default): Linear(in_features=64, out_features=1024, bias=False)
|
| 89 |
+
)
|
| 90 |
+
(lora_embedding_A): ParameterDict()
|
| 91 |
+
(lora_embedding_B): ParameterDict()
|
| 92 |
+
)
|
| 93 |
+
(o_proj): lora.Linear(
|
| 94 |
+
(base_layer): Linear(in_features=4096, out_features=4096, bias=False)
|
| 95 |
+
(lora_dropout): ModuleDict(
|
| 96 |
+
(default): Dropout(p=0.05, inplace=False)
|
| 97 |
+
)
|
| 98 |
+
(lora_A): ModuleDict(
|
| 99 |
+
(default): Linear(in_features=4096, out_features=64, bias=False)
|
| 100 |
+
)
|
| 101 |
+
(lora_B): ModuleDict(
|
| 102 |
+
(default): Linear(in_features=64, out_features=4096, bias=False)
|
| 103 |
+
)
|
| 104 |
+
(lora_embedding_A): ParameterDict()
|
| 105 |
+
(lora_embedding_B): ParameterDict()
|
| 106 |
+
)
|
| 107 |
+
(rotary_emb): MistralRotaryEmbedding()
|
| 108 |
+
)
|
| 109 |
+
(mlp): MistralMLP(
|
| 110 |
+
(gate_proj): lora.Linear(
|
| 111 |
+
(base_layer): Linear(in_features=4096, out_features=14336, bias=False)
|
| 112 |
+
(lora_dropout): ModuleDict(
|
| 113 |
+
(default): Dropout(p=0.05, inplace=False)
|
| 114 |
+
)
|
| 115 |
+
(lora_A): ModuleDict(
|
| 116 |
+
(default): Linear(in_features=4096, out_features=64, bias=False)
|
| 117 |
+
)
|
| 118 |
+
(lora_B): ModuleDict(
|
| 119 |
+
(default): Linear(in_features=64, out_features=14336, bias=False)
|
| 120 |
+
)
|
| 121 |
+
(lora_embedding_A): ParameterDict()
|
| 122 |
+
(lora_embedding_B): ParameterDict()
|
| 123 |
+
)
|
| 124 |
+
(up_proj): lora.Linear(
|
| 125 |
+
(base_layer): Linear(in_features=4096, out_features=14336, bias=False)
|
| 126 |
+
(lora_dropout): ModuleDict(
|
| 127 |
+
(default): Dropout(p=0.05, inplace=False)
|
| 128 |
+
)
|
| 129 |
+
(lora_A): ModuleDict(
|
| 130 |
+
(default): Linear(in_features=4096, out_features=64, bias=False)
|
| 131 |
+
)
|
| 132 |
+
(lora_B): ModuleDict(
|
| 133 |
+
(default): Linear(in_features=64, out_features=14336, bias=False)
|
| 134 |
+
)
|
| 135 |
+
(lora_embedding_A): ParameterDict()
|
| 136 |
+
(lora_embedding_B): ParameterDict()
|
| 137 |
+
)
|
| 138 |
+
(down_proj): lora.Linear(
|
| 139 |
+
(base_layer): Linear(in_features=14336, out_features=4096, bias=False)
|
| 140 |
+
(lora_dropout): ModuleDict(
|
| 141 |
+
(default): Dropout(p=0.05, inplace=False)
|
| 142 |
+
)
|
| 143 |
+
(lora_A): ModuleDict(
|
| 144 |
+
(default): Linear(in_features=14336, out_features=64, bias=False)
|
| 145 |
+
)
|
| 146 |
+
(lora_B): ModuleDict(
|
| 147 |
+
(default): Linear(in_features=64, out_features=4096, bias=False)
|
| 148 |
+
)
|
| 149 |
+
(lora_embedding_A): ParameterDict()
|
| 150 |
+
(lora_embedding_B): ParameterDict()
|
| 151 |
+
)
|
| 152 |
+
(act_fn): SiLU()
|
| 153 |
+
)
|
| 154 |
+
(input_layernorm): MistralRMSNorm()
|
| 155 |
+
(post_attention_layernorm): MistralRMSNorm()
|
| 156 |
+
)
|
| 157 |
+
)
|
| 158 |
+
(norm): MistralRMSNorm()
|
| 159 |
+
(vision_clip_lmm_projector): Sequential(
|
| 160 |
+
(0): Linear(in_features=1024, out_features=4096, bias=True)
|
| 161 |
+
(1): GELU(approximate='none')
|
| 162 |
+
(2): Linear(in_features=4096, out_features=4096, bias=True)
|
| 163 |
+
)
|
| 164 |
+
)
|
| 165 |
+
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
|
| 166 |
+
)
|
| 167 |
+
)
|
| 168 |
+
)
|
| 169 |
+
```
|
| 170 |
+
|
| 171 |
+
### Framework versions
|
| 172 |
+
|
| 173 |
+
- PEFT 0.10.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e47be90f9f4ce25fbcd39f23e259812fe1d53a2fcf5f777995a06d3473dd2814
|
| 3 |
+
size 335605144
|
checkpoint-2000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-2000/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
+
"v_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
checkpoint-2000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e47be90f9f4ce25fbcd39f23e259812fe1d53a2fcf5f777995a06d3473dd2814
|
| 3 |
+
size 335605144
|
checkpoint-2000/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"modalities": [
|
| 15 |
+
"vision_clip"
|
| 16 |
+
],
|
| 17 |
+
"modality_builder": "vision_clip",
|
| 18 |
+
"model_cls": "MistralLMMForCausalLM",
|
| 19 |
+
"model_type": "mistral-lmm",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_experts_per_tok": 2,
|
| 22 |
+
"num_hidden_layers": 32,
|
| 23 |
+
"num_key_value_heads": 8,
|
| 24 |
+
"num_local_experts": 8,
|
| 25 |
+
"output_router_logits": false,
|
| 26 |
+
"rms_norm_eps": 1e-05,
|
| 27 |
+
"rope_theta": 1000000.0,
|
| 28 |
+
"router_aux_loss_coef": 0.02,
|
| 29 |
+
"sliding_window": null,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.40.1",
|
| 33 |
+
"use_cache": false,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
checkpoint-2000/global_step2000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f00c0a439e852c062c0abb46613c64783569e3be668d8710abaac29b04578bc
|
| 3 |
+
size 251761335
|
checkpoint-2000/global_step2000/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9e41a656706dbfca9f32697a8d93ca097dd3ef3d817fba3b9c564e3282d0f10
|
| 3 |
+
size 29680771757
|
checkpoint-2000/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step2000
|
checkpoint-2000/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5007350502df6c02448c658b9321fddb2488e1fa4dec7088b8f6cd6208a20265
|
| 3 |
+
size 41961255
|
checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bc778ca04eaa15e439c090637842cc48df852e98bf79e1922478ba8602e4caa
|
| 3 |
+
size 14575
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf6824046aa2a743eebe05536b66cd7b358bc4acd0b9981d5643779b0fb6efe5
|
| 3 |
+
size 627
|
checkpoint-2000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": "<unk>",
|
| 10 |
+
"eos_token": {
|
| 11 |
+
"content": "</s>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
"mask_token": "<unk>",
|
| 18 |
+
"pad_token": "<unk>",
|
| 19 |
+
"sep_token": "<unk>",
|
| 20 |
+
"unk_token": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
}
|
| 27 |
+
}
|
checkpoint-2000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-2000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"cls_token": "<unk>",
|
| 36 |
+
"eos_token": "</s>",
|
| 37 |
+
"legacy": true,
|
| 38 |
+
"mask_token": "<unk>",
|
| 39 |
+
"model_max_length": 2048,
|
| 40 |
+
"pad_token": "<unk>",
|
| 41 |
+
"padding_side": "right",
|
| 42 |
+
"sep_token": "<unk>",
|
| 43 |
+
"sp_model_kwargs": {},
|
| 44 |
+
"spaces_between_special_tokens": false,
|
| 45 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
+
"unk_token": "<unk>",
|
| 47 |
+
"use_default_system_prompt": false
|
| 48 |
+
}
|
checkpoint-2000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f3728bcc6e19d69628a86059c42b19e48bf9eaee9b99e6319f69a59242d2de8
|
| 3 |
+
size 5947
|
checkpoint-2000/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,578 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
| 14 |
+
|
| 15 |
+
import argparse
|
| 16 |
+
import torch
|
| 17 |
+
import glob
|
| 18 |
+
import math
|
| 19 |
+
import os
|
| 20 |
+
import re
|
| 21 |
+
from collections import OrderedDict
|
| 22 |
+
from dataclasses import dataclass
|
| 23 |
+
|
| 24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 26 |
+
from deepspeed.utils import logger
|
| 27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
@dataclass
|
| 33 |
+
class zero_model_state:
|
| 34 |
+
buffers: dict()
|
| 35 |
+
param_shapes: dict()
|
| 36 |
+
shared_params: list
|
| 37 |
+
ds_version: int
|
| 38 |
+
frozen_param_shapes: dict()
|
| 39 |
+
frozen_param_fragments: dict()
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
debug = 0
|
| 43 |
+
|
| 44 |
+
# load to cpu
|
| 45 |
+
device = torch.device('cpu')
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
def atoi(text):
|
| 49 |
+
return int(text) if text.isdigit() else text
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def natural_keys(text):
|
| 53 |
+
'''
|
| 54 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 56 |
+
(See Toothy's implementation in the comments)
|
| 57 |
+
'''
|
| 58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 62 |
+
if not os.path.isdir(checkpoint_dir):
|
| 63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 64 |
+
|
| 65 |
+
# there should be only one file
|
| 66 |
+
if zero_stage == 2:
|
| 67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 68 |
+
elif zero_stage == 3:
|
| 69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 70 |
+
|
| 71 |
+
if not os.path.exists(file):
|
| 72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 73 |
+
|
| 74 |
+
return file
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 80 |
+
|
| 81 |
+
if len(ckpt_files) == 0:
|
| 82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 83 |
+
|
| 84 |
+
return ckpt_files
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def get_optim_files(checkpoint_dir):
|
| 88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def get_model_state_files(checkpoint_dir):
|
| 92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def parse_model_states(files):
|
| 96 |
+
zero_model_states = []
|
| 97 |
+
for file in files:
|
| 98 |
+
state_dict = torch.load(file, map_location=device)
|
| 99 |
+
|
| 100 |
+
if BUFFER_NAMES not in state_dict:
|
| 101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 103 |
+
if debug:
|
| 104 |
+
print("Found buffers:", buffer_names)
|
| 105 |
+
|
| 106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 109 |
+
|
| 110 |
+
# collect parameters that are included in param_shapes
|
| 111 |
+
param_names = []
|
| 112 |
+
for s in param_shapes:
|
| 113 |
+
for name in s.keys():
|
| 114 |
+
param_names.append(name)
|
| 115 |
+
|
| 116 |
+
# update with frozen parameters
|
| 117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 118 |
+
if frozen_param_shapes is not None:
|
| 119 |
+
if debug:
|
| 120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 121 |
+
param_names += list(frozen_param_shapes.keys())
|
| 122 |
+
|
| 123 |
+
# handle shared params
|
| 124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 125 |
+
|
| 126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 127 |
+
|
| 128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 129 |
+
|
| 130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 131 |
+
param_shapes=param_shapes,
|
| 132 |
+
shared_params=shared_params,
|
| 133 |
+
ds_version=ds_version,
|
| 134 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 135 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 136 |
+
zero_model_states.append(z_model_state)
|
| 137 |
+
|
| 138 |
+
return zero_model_states
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 142 |
+
|
| 143 |
+
total_files = len(files)
|
| 144 |
+
state_dicts = []
|
| 145 |
+
for f in files:
|
| 146 |
+
state_dicts.append(torch.load(f, map_location=device))
|
| 147 |
+
|
| 148 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 149 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 150 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 151 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 152 |
+
|
| 153 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 154 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 155 |
+
# use the max of the partition_count to get the dp world_size.
|
| 156 |
+
|
| 157 |
+
if type(world_size) is list:
|
| 158 |
+
world_size = max(world_size)
|
| 159 |
+
|
| 160 |
+
if world_size != total_files:
|
| 161 |
+
raise ValueError(
|
| 162 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 163 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 164 |
+
)
|
| 165 |
+
|
| 166 |
+
# the groups are named differently in each stage
|
| 167 |
+
if zero_stage == 2:
|
| 168 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 169 |
+
elif zero_stage == 3:
|
| 170 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 171 |
+
else:
|
| 172 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 173 |
+
|
| 174 |
+
if zero_stage == 2:
|
| 175 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 176 |
+
elif zero_stage == 3:
|
| 177 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 178 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 179 |
+
#
|
| 180 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 181 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 182 |
+
|
| 183 |
+
fp32_flat_groups = [
|
| 184 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 185 |
+
]
|
| 186 |
+
|
| 187 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
|
| 191 |
+
"""
|
| 192 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 193 |
+
|
| 194 |
+
Args:
|
| 195 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 196 |
+
|
| 197 |
+
"""
|
| 198 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 199 |
+
|
| 200 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 201 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 202 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 203 |
+
|
| 204 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 205 |
+
|
| 206 |
+
zero_model_states = parse_model_states(model_files)
|
| 207 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 208 |
+
|
| 209 |
+
if zero_stage == 2:
|
| 210 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
| 211 |
+
elif zero_stage == 3:
|
| 212 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 248 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 249 |
+
|
| 250 |
+
# Reconstruction protocol:
|
| 251 |
+
#
|
| 252 |
+
# XXX: document this
|
| 253 |
+
|
| 254 |
+
if debug:
|
| 255 |
+
for i in range(world_size):
|
| 256 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 257 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 258 |
+
|
| 259 |
+
# XXX: memory usage doubles here (zero2)
|
| 260 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 261 |
+
merged_single_partition_of_fp32_groups = []
|
| 262 |
+
for i in range(num_param_groups):
|
| 263 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 264 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 265 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 266 |
+
avail_numel = sum(
|
| 267 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 268 |
+
|
| 269 |
+
if debug:
|
| 270 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 271 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 272 |
+
# not asserting if there is a mismatch due to possible padding
|
| 273 |
+
print(f"Have {avail_numel} numels to process.")
|
| 274 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 275 |
+
|
| 276 |
+
# params
|
| 277 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 278 |
+
# out-of-core computing solution
|
| 279 |
+
total_numel = 0
|
| 280 |
+
total_params = 0
|
| 281 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 282 |
+
offset = 0
|
| 283 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 284 |
+
for name, shape in shapes.items():
|
| 285 |
+
|
| 286 |
+
unpartitioned_numel = shape.numel()
|
| 287 |
+
total_numel += unpartitioned_numel
|
| 288 |
+
total_params += 1
|
| 289 |
+
|
| 290 |
+
if debug:
|
| 291 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 292 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 293 |
+
offset += unpartitioned_numel
|
| 294 |
+
|
| 295 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 296 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 297 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 298 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 299 |
+
align_to = 2 * world_size
|
| 300 |
+
|
| 301 |
+
def zero2_align(x):
|
| 302 |
+
return align_to * math.ceil(x / align_to)
|
| 303 |
+
|
| 304 |
+
if debug:
|
| 305 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 306 |
+
|
| 307 |
+
offset = zero2_align(offset)
|
| 308 |
+
avail_numel = zero2_align(avail_numel)
|
| 309 |
+
|
| 310 |
+
if debug:
|
| 311 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 312 |
+
|
| 313 |
+
# Sanity check
|
| 314 |
+
if offset != avail_numel:
|
| 315 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 316 |
+
|
| 317 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 318 |
+
|
| 319 |
+
|
| 320 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
| 321 |
+
state_dict = OrderedDict()
|
| 322 |
+
|
| 323 |
+
# buffers
|
| 324 |
+
buffers = zero_model_states[0].buffers
|
| 325 |
+
state_dict.update(buffers)
|
| 326 |
+
if debug:
|
| 327 |
+
print(f"added {len(buffers)} buffers")
|
| 328 |
+
|
| 329 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 330 |
+
|
| 331 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 332 |
+
|
| 333 |
+
# recover shared parameters
|
| 334 |
+
for pair in zero_model_states[0].shared_params:
|
| 335 |
+
if pair[1] in state_dict:
|
| 336 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 337 |
+
|
| 338 |
+
return state_dict
|
| 339 |
+
|
| 340 |
+
|
| 341 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 342 |
+
remainder = unpartitioned_numel % world_size
|
| 343 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 344 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 345 |
+
return partitioned_numel, padding_numel
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 349 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 350 |
+
return
|
| 351 |
+
|
| 352 |
+
if debug:
|
| 353 |
+
for i in range(world_size):
|
| 354 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 355 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 356 |
+
|
| 357 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 358 |
+
wanted_params = len(frozen_param_shapes)
|
| 359 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 360 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 361 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 362 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 363 |
+
|
| 364 |
+
total_params = 0
|
| 365 |
+
total_numel = 0
|
| 366 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 367 |
+
total_params += 1
|
| 368 |
+
unpartitioned_numel = shape.numel()
|
| 369 |
+
total_numel += unpartitioned_numel
|
| 370 |
+
|
| 371 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 372 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 373 |
+
|
| 374 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 375 |
+
|
| 376 |
+
if debug:
|
| 377 |
+
print(
|
| 378 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 379 |
+
)
|
| 380 |
+
|
| 381 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 382 |
+
|
| 383 |
+
|
| 384 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 385 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 386 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 387 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 388 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 389 |
+
|
| 390 |
+
# merge list of dicts, preserving order
|
| 391 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 392 |
+
|
| 393 |
+
if debug:
|
| 394 |
+
for i in range(world_size):
|
| 395 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 396 |
+
|
| 397 |
+
wanted_params = len(param_shapes)
|
| 398 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 399 |
+
# not asserting if there is a mismatch due to possible padding
|
| 400 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 401 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 402 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 403 |
+
|
| 404 |
+
# params
|
| 405 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 406 |
+
# out-of-core computing solution
|
| 407 |
+
offset = 0
|
| 408 |
+
total_numel = 0
|
| 409 |
+
total_params = 0
|
| 410 |
+
for name, shape in param_shapes.items():
|
| 411 |
+
|
| 412 |
+
unpartitioned_numel = shape.numel()
|
| 413 |
+
total_numel += unpartitioned_numel
|
| 414 |
+
total_params += 1
|
| 415 |
+
|
| 416 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 417 |
+
|
| 418 |
+
if debug:
|
| 419 |
+
print(
|
| 420 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 421 |
+
)
|
| 422 |
+
|
| 423 |
+
# XXX: memory usage doubles here
|
| 424 |
+
state_dict[name] = torch.cat(
|
| 425 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 426 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 427 |
+
offset += partitioned_numel
|
| 428 |
+
|
| 429 |
+
offset *= world_size
|
| 430 |
+
|
| 431 |
+
# Sanity check
|
| 432 |
+
if offset != avail_numel:
|
| 433 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 434 |
+
|
| 435 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 436 |
+
|
| 437 |
+
|
| 438 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
| 439 |
+
state_dict = OrderedDict()
|
| 440 |
+
|
| 441 |
+
# buffers
|
| 442 |
+
buffers = zero_model_states[0].buffers
|
| 443 |
+
state_dict.update(buffers)
|
| 444 |
+
if debug:
|
| 445 |
+
print(f"added {len(buffers)} buffers")
|
| 446 |
+
|
| 447 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 448 |
+
|
| 449 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 450 |
+
|
| 451 |
+
# recover shared parameters
|
| 452 |
+
for pair in zero_model_states[0].shared_params:
|
| 453 |
+
if pair[1] in state_dict:
|
| 454 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 455 |
+
|
| 456 |
+
return state_dict
|
| 457 |
+
|
| 458 |
+
|
| 459 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
|
| 460 |
+
"""
|
| 461 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 462 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 463 |
+
via a model hub.
|
| 464 |
+
|
| 465 |
+
Args:
|
| 466 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 467 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 468 |
+
|
| 469 |
+
Returns:
|
| 470 |
+
- pytorch ``state_dict``
|
| 471 |
+
|
| 472 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 473 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 474 |
+
the checkpoint.
|
| 475 |
+
|
| 476 |
+
A typical usage might be ::
|
| 477 |
+
|
| 478 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 479 |
+
# do the training and checkpoint saving
|
| 480 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 481 |
+
model = model.cpu() # move to cpu
|
| 482 |
+
model.load_state_dict(state_dict)
|
| 483 |
+
# submit to model hub or save the model to share with others
|
| 484 |
+
|
| 485 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 486 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 487 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 488 |
+
|
| 489 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 490 |
+
|
| 491 |
+
"""
|
| 492 |
+
if tag is None:
|
| 493 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 494 |
+
if os.path.isfile(latest_path):
|
| 495 |
+
with open(latest_path, 'r') as fd:
|
| 496 |
+
tag = fd.read().strip()
|
| 497 |
+
else:
|
| 498 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 499 |
+
|
| 500 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 501 |
+
|
| 502 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 503 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 504 |
+
|
| 505 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
|
| 506 |
+
|
| 507 |
+
|
| 508 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
|
| 509 |
+
"""
|
| 510 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 511 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 512 |
+
|
| 513 |
+
Args:
|
| 514 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 515 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
| 516 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 517 |
+
"""
|
| 518 |
+
|
| 519 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 520 |
+
print(f"Saving fp32 state dict to {output_file}")
|
| 521 |
+
torch.save(state_dict, output_file)
|
| 522 |
+
|
| 523 |
+
|
| 524 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 525 |
+
"""
|
| 526 |
+
1. Put the provided model to cpu
|
| 527 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 528 |
+
3. Load it into the provided model
|
| 529 |
+
|
| 530 |
+
Args:
|
| 531 |
+
- ``model``: the model object to update
|
| 532 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 533 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 534 |
+
|
| 535 |
+
Returns:
|
| 536 |
+
- ``model`: modified model
|
| 537 |
+
|
| 538 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 539 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 540 |
+
conveniently placed for you in the checkpoint folder.
|
| 541 |
+
|
| 542 |
+
A typical usage might be ::
|
| 543 |
+
|
| 544 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 545 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 546 |
+
# submit to model hub or save the model to share with others
|
| 547 |
+
|
| 548 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 549 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 550 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 551 |
+
|
| 552 |
+
"""
|
| 553 |
+
logger.info(f"Extracting fp32 weights")
|
| 554 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 555 |
+
|
| 556 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 557 |
+
model = model.cpu()
|
| 558 |
+
model.load_state_dict(state_dict, strict=False)
|
| 559 |
+
|
| 560 |
+
return model
|
| 561 |
+
|
| 562 |
+
|
| 563 |
+
if __name__ == "__main__":
|
| 564 |
+
|
| 565 |
+
parser = argparse.ArgumentParser()
|
| 566 |
+
parser.add_argument("checkpoint_dir",
|
| 567 |
+
type=str,
|
| 568 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 569 |
+
parser.add_argument(
|
| 570 |
+
"output_file",
|
| 571 |
+
type=str,
|
| 572 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
| 573 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 574 |
+
args = parser.parse_args()
|
| 575 |
+
|
| 576 |
+
debug = args.debug
|
| 577 |
+
|
| 578 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"modalities": [
|
| 15 |
+
"vision_clip"
|
| 16 |
+
],
|
| 17 |
+
"modality_builder": "vision_clip",
|
| 18 |
+
"model_cls": "MistralLMMForCausalLM",
|
| 19 |
+
"model_type": "mistral-lmm",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_experts_per_tok": 2,
|
| 22 |
+
"num_hidden_layers": 32,
|
| 23 |
+
"num_key_value_heads": 8,
|
| 24 |
+
"num_local_experts": 8,
|
| 25 |
+
"output_router_logits": false,
|
| 26 |
+
"rms_norm_eps": 1e-05,
|
| 27 |
+
"rope_theta": 1000000.0,
|
| 28 |
+
"router_aux_loss_coef": 0.02,
|
| 29 |
+
"sliding_window": null,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.40.1",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
model_named_parameters.txt
ADDED
|
@@ -0,0 +1,743 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
base_model.model.model.embed_tokens.weight torch.Size([32000, 4096]) False
|
| 2 |
+
base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 3 |
+
base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 4 |
+
base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 5 |
+
base_model.model.model.layers.0.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 6 |
+
base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 7 |
+
base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 8 |
+
base_model.model.model.layers.0.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 9 |
+
base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 10 |
+
base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 11 |
+
base_model.model.model.layers.0.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 12 |
+
base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 13 |
+
base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 14 |
+
base_model.model.model.layers.0.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 15 |
+
base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 16 |
+
base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 17 |
+
base_model.model.model.layers.0.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 18 |
+
base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 19 |
+
base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 20 |
+
base_model.model.model.layers.0.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 21 |
+
base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 22 |
+
base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 23 |
+
base_model.model.model.layers.0.input_layernorm.weight torch.Size([4096]) False
|
| 24 |
+
base_model.model.model.layers.0.post_attention_layernorm.weight torch.Size([4096]) False
|
| 25 |
+
base_model.model.model.layers.1.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 26 |
+
base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 27 |
+
base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 28 |
+
base_model.model.model.layers.1.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 29 |
+
base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 30 |
+
base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 31 |
+
base_model.model.model.layers.1.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 32 |
+
base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 33 |
+
base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 34 |
+
base_model.model.model.layers.1.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 35 |
+
base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 36 |
+
base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 37 |
+
base_model.model.model.layers.1.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 38 |
+
base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 39 |
+
base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 40 |
+
base_model.model.model.layers.1.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 41 |
+
base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 42 |
+
base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 43 |
+
base_model.model.model.layers.1.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 44 |
+
base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 45 |
+
base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 46 |
+
base_model.model.model.layers.1.input_layernorm.weight torch.Size([4096]) False
|
| 47 |
+
base_model.model.model.layers.1.post_attention_layernorm.weight torch.Size([4096]) False
|
| 48 |
+
base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 49 |
+
base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 50 |
+
base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 51 |
+
base_model.model.model.layers.2.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 52 |
+
base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 53 |
+
base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 54 |
+
base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 55 |
+
base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 56 |
+
base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 57 |
+
base_model.model.model.layers.2.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 58 |
+
base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 59 |
+
base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 60 |
+
base_model.model.model.layers.2.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 61 |
+
base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 62 |
+
base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 63 |
+
base_model.model.model.layers.2.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 64 |
+
base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 65 |
+
base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 66 |
+
base_model.model.model.layers.2.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 67 |
+
base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 68 |
+
base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 69 |
+
base_model.model.model.layers.2.input_layernorm.weight torch.Size([4096]) False
|
| 70 |
+
base_model.model.model.layers.2.post_attention_layernorm.weight torch.Size([4096]) False
|
| 71 |
+
base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 72 |
+
base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 73 |
+
base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 74 |
+
base_model.model.model.layers.3.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 75 |
+
base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 76 |
+
base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 77 |
+
base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 78 |
+
base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 79 |
+
base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 80 |
+
base_model.model.model.layers.3.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 81 |
+
base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 82 |
+
base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 83 |
+
base_model.model.model.layers.3.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 84 |
+
base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 85 |
+
base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 86 |
+
base_model.model.model.layers.3.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 87 |
+
base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 88 |
+
base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 89 |
+
base_model.model.model.layers.3.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 90 |
+
base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 91 |
+
base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 92 |
+
base_model.model.model.layers.3.input_layernorm.weight torch.Size([4096]) False
|
| 93 |
+
base_model.model.model.layers.3.post_attention_layernorm.weight torch.Size([4096]) False
|
| 94 |
+
base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 95 |
+
base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 96 |
+
base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 97 |
+
base_model.model.model.layers.4.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 98 |
+
base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 99 |
+
base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 100 |
+
base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 101 |
+
base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 102 |
+
base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 103 |
+
base_model.model.model.layers.4.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 104 |
+
base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 105 |
+
base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 106 |
+
base_model.model.model.layers.4.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 107 |
+
base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 108 |
+
base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 109 |
+
base_model.model.model.layers.4.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 110 |
+
base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 111 |
+
base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 112 |
+
base_model.model.model.layers.4.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 113 |
+
base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 114 |
+
base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 115 |
+
base_model.model.model.layers.4.input_layernorm.weight torch.Size([4096]) False
|
| 116 |
+
base_model.model.model.layers.4.post_attention_layernorm.weight torch.Size([4096]) False
|
| 117 |
+
base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 118 |
+
base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 119 |
+
base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 120 |
+
base_model.model.model.layers.5.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 121 |
+
base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 122 |
+
base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 123 |
+
base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 124 |
+
base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 125 |
+
base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 126 |
+
base_model.model.model.layers.5.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 127 |
+
base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 128 |
+
base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 129 |
+
base_model.model.model.layers.5.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 130 |
+
base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 131 |
+
base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 132 |
+
base_model.model.model.layers.5.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 133 |
+
base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 134 |
+
base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 135 |
+
base_model.model.model.layers.5.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 136 |
+
base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 137 |
+
base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 138 |
+
base_model.model.model.layers.5.input_layernorm.weight torch.Size([4096]) False
|
| 139 |
+
base_model.model.model.layers.5.post_attention_layernorm.weight torch.Size([4096]) False
|
| 140 |
+
base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 141 |
+
base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 142 |
+
base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 143 |
+
base_model.model.model.layers.6.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 144 |
+
base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 145 |
+
base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 146 |
+
base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 147 |
+
base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 148 |
+
base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 149 |
+
base_model.model.model.layers.6.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 150 |
+
base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 151 |
+
base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 152 |
+
base_model.model.model.layers.6.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 153 |
+
base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 154 |
+
base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 155 |
+
base_model.model.model.layers.6.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 156 |
+
base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 157 |
+
base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 158 |
+
base_model.model.model.layers.6.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 159 |
+
base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 160 |
+
base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 161 |
+
base_model.model.model.layers.6.input_layernorm.weight torch.Size([4096]) False
|
| 162 |
+
base_model.model.model.layers.6.post_attention_layernorm.weight torch.Size([4096]) False
|
| 163 |
+
base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 164 |
+
base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 165 |
+
base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 166 |
+
base_model.model.model.layers.7.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 167 |
+
base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 168 |
+
base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 169 |
+
base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 170 |
+
base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 171 |
+
base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 172 |
+
base_model.model.model.layers.7.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 173 |
+
base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 174 |
+
base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 175 |
+
base_model.model.model.layers.7.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 176 |
+
base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 177 |
+
base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 178 |
+
base_model.model.model.layers.7.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 179 |
+
base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 180 |
+
base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 181 |
+
base_model.model.model.layers.7.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 182 |
+
base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 183 |
+
base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 184 |
+
base_model.model.model.layers.7.input_layernorm.weight torch.Size([4096]) False
|
| 185 |
+
base_model.model.model.layers.7.post_attention_layernorm.weight torch.Size([4096]) False
|
| 186 |
+
base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 187 |
+
base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 188 |
+
base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 189 |
+
base_model.model.model.layers.8.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 190 |
+
base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 191 |
+
base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 192 |
+
base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 193 |
+
base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 194 |
+
base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 195 |
+
base_model.model.model.layers.8.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 196 |
+
base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 197 |
+
base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 198 |
+
base_model.model.model.layers.8.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 199 |
+
base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 200 |
+
base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 201 |
+
base_model.model.model.layers.8.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 202 |
+
base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 203 |
+
base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 204 |
+
base_model.model.model.layers.8.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 205 |
+
base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 206 |
+
base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 207 |
+
base_model.model.model.layers.8.input_layernorm.weight torch.Size([4096]) False
|
| 208 |
+
base_model.model.model.layers.8.post_attention_layernorm.weight torch.Size([4096]) False
|
| 209 |
+
base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 210 |
+
base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 211 |
+
base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 212 |
+
base_model.model.model.layers.9.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 213 |
+
base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 214 |
+
base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 215 |
+
base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 216 |
+
base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 217 |
+
base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 218 |
+
base_model.model.model.layers.9.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 219 |
+
base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 220 |
+
base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 221 |
+
base_model.model.model.layers.9.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 222 |
+
base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 223 |
+
base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 224 |
+
base_model.model.model.layers.9.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 225 |
+
base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 226 |
+
base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 227 |
+
base_model.model.model.layers.9.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 228 |
+
base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 229 |
+
base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 230 |
+
base_model.model.model.layers.9.input_layernorm.weight torch.Size([4096]) False
|
| 231 |
+
base_model.model.model.layers.9.post_attention_layernorm.weight torch.Size([4096]) False
|
| 232 |
+
base_model.model.model.layers.10.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 233 |
+
base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 234 |
+
base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 235 |
+
base_model.model.model.layers.10.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 236 |
+
base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 237 |
+
base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 238 |
+
base_model.model.model.layers.10.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 239 |
+
base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 240 |
+
base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 241 |
+
base_model.model.model.layers.10.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 242 |
+
base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 243 |
+
base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 244 |
+
base_model.model.model.layers.10.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 245 |
+
base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 246 |
+
base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 247 |
+
base_model.model.model.layers.10.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 248 |
+
base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 249 |
+
base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 250 |
+
base_model.model.model.layers.10.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 251 |
+
base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 252 |
+
base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 253 |
+
base_model.model.model.layers.10.input_layernorm.weight torch.Size([4096]) False
|
| 254 |
+
base_model.model.model.layers.10.post_attention_layernorm.weight torch.Size([4096]) False
|
| 255 |
+
base_model.model.model.layers.11.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 256 |
+
base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 257 |
+
base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 258 |
+
base_model.model.model.layers.11.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 259 |
+
base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 260 |
+
base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 261 |
+
base_model.model.model.layers.11.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 262 |
+
base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 263 |
+
base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 264 |
+
base_model.model.model.layers.11.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 265 |
+
base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 266 |
+
base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 267 |
+
base_model.model.model.layers.11.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 268 |
+
base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 269 |
+
base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 270 |
+
base_model.model.model.layers.11.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 271 |
+
base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 272 |
+
base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 273 |
+
base_model.model.model.layers.11.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 274 |
+
base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 275 |
+
base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 276 |
+
base_model.model.model.layers.11.input_layernorm.weight torch.Size([4096]) False
|
| 277 |
+
base_model.model.model.layers.11.post_attention_layernorm.weight torch.Size([4096]) False
|
| 278 |
+
base_model.model.model.layers.12.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 279 |
+
base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 280 |
+
base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 281 |
+
base_model.model.model.layers.12.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 282 |
+
base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 283 |
+
base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 284 |
+
base_model.model.model.layers.12.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 285 |
+
base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 286 |
+
base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 287 |
+
base_model.model.model.layers.12.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 288 |
+
base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 289 |
+
base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 290 |
+
base_model.model.model.layers.12.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 291 |
+
base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 292 |
+
base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 293 |
+
base_model.model.model.layers.12.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 294 |
+
base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 295 |
+
base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 296 |
+
base_model.model.model.layers.12.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 297 |
+
base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 298 |
+
base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 299 |
+
base_model.model.model.layers.12.input_layernorm.weight torch.Size([4096]) False
|
| 300 |
+
base_model.model.model.layers.12.post_attention_layernorm.weight torch.Size([4096]) False
|
| 301 |
+
base_model.model.model.layers.13.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 302 |
+
base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 303 |
+
base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 304 |
+
base_model.model.model.layers.13.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 305 |
+
base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 306 |
+
base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 307 |
+
base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 308 |
+
base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 309 |
+
base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 310 |
+
base_model.model.model.layers.13.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 311 |
+
base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 312 |
+
base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 313 |
+
base_model.model.model.layers.13.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 314 |
+
base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 315 |
+
base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 316 |
+
base_model.model.model.layers.13.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 317 |
+
base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 318 |
+
base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 319 |
+
base_model.model.model.layers.13.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 320 |
+
base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 321 |
+
base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 322 |
+
base_model.model.model.layers.13.input_layernorm.weight torch.Size([4096]) False
|
| 323 |
+
base_model.model.model.layers.13.post_attention_layernorm.weight torch.Size([4096]) False
|
| 324 |
+
base_model.model.model.layers.14.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 325 |
+
base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 326 |
+
base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 327 |
+
base_model.model.model.layers.14.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 328 |
+
base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 329 |
+
base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 330 |
+
base_model.model.model.layers.14.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 331 |
+
base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 332 |
+
base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 333 |
+
base_model.model.model.layers.14.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 334 |
+
base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 335 |
+
base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 336 |
+
base_model.model.model.layers.14.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 337 |
+
base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 338 |
+
base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 339 |
+
base_model.model.model.layers.14.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 340 |
+
base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 341 |
+
base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 342 |
+
base_model.model.model.layers.14.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 343 |
+
base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 344 |
+
base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 345 |
+
base_model.model.model.layers.14.input_layernorm.weight torch.Size([4096]) False
|
| 346 |
+
base_model.model.model.layers.14.post_attention_layernorm.weight torch.Size([4096]) False
|
| 347 |
+
base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 348 |
+
base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 349 |
+
base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 350 |
+
base_model.model.model.layers.15.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 351 |
+
base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 352 |
+
base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 353 |
+
base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 354 |
+
base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 355 |
+
base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 356 |
+
base_model.model.model.layers.15.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 357 |
+
base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 358 |
+
base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 359 |
+
base_model.model.model.layers.15.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 360 |
+
base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 361 |
+
base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 362 |
+
base_model.model.model.layers.15.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 363 |
+
base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 364 |
+
base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 365 |
+
base_model.model.model.layers.15.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 366 |
+
base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 367 |
+
base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 368 |
+
base_model.model.model.layers.15.input_layernorm.weight torch.Size([4096]) False
|
| 369 |
+
base_model.model.model.layers.15.post_attention_layernorm.weight torch.Size([4096]) False
|
| 370 |
+
base_model.model.model.layers.16.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 371 |
+
base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 372 |
+
base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 373 |
+
base_model.model.model.layers.16.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 374 |
+
base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 375 |
+
base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 376 |
+
base_model.model.model.layers.16.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 377 |
+
base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 378 |
+
base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 379 |
+
base_model.model.model.layers.16.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 380 |
+
base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 381 |
+
base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 382 |
+
base_model.model.model.layers.16.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 383 |
+
base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 384 |
+
base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 385 |
+
base_model.model.model.layers.16.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 386 |
+
base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 387 |
+
base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 388 |
+
base_model.model.model.layers.16.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 389 |
+
base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 390 |
+
base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 391 |
+
base_model.model.model.layers.16.input_layernorm.weight torch.Size([4096]) False
|
| 392 |
+
base_model.model.model.layers.16.post_attention_layernorm.weight torch.Size([4096]) False
|
| 393 |
+
base_model.model.model.layers.17.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 394 |
+
base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 395 |
+
base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 396 |
+
base_model.model.model.layers.17.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 397 |
+
base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 398 |
+
base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 399 |
+
base_model.model.model.layers.17.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 400 |
+
base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 401 |
+
base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 402 |
+
base_model.model.model.layers.17.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 403 |
+
base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 404 |
+
base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 405 |
+
base_model.model.model.layers.17.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 406 |
+
base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 407 |
+
base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 408 |
+
base_model.model.model.layers.17.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 409 |
+
base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 410 |
+
base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 411 |
+
base_model.model.model.layers.17.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 412 |
+
base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 413 |
+
base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 414 |
+
base_model.model.model.layers.17.input_layernorm.weight torch.Size([4096]) False
|
| 415 |
+
base_model.model.model.layers.17.post_attention_layernorm.weight torch.Size([4096]) False
|
| 416 |
+
base_model.model.model.layers.18.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 417 |
+
base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 418 |
+
base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 419 |
+
base_model.model.model.layers.18.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 420 |
+
base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 421 |
+
base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 422 |
+
base_model.model.model.layers.18.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 423 |
+
base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 424 |
+
base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 425 |
+
base_model.model.model.layers.18.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 426 |
+
base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 427 |
+
base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 428 |
+
base_model.model.model.layers.18.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 429 |
+
base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 430 |
+
base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 431 |
+
base_model.model.model.layers.18.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 432 |
+
base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 433 |
+
base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 434 |
+
base_model.model.model.layers.18.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 435 |
+
base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 436 |
+
base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 437 |
+
base_model.model.model.layers.18.input_layernorm.weight torch.Size([4096]) False
|
| 438 |
+
base_model.model.model.layers.18.post_attention_layernorm.weight torch.Size([4096]) False
|
| 439 |
+
base_model.model.model.layers.19.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 440 |
+
base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 441 |
+
base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 442 |
+
base_model.model.model.layers.19.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 443 |
+
base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 444 |
+
base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 445 |
+
base_model.model.model.layers.19.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 446 |
+
base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 447 |
+
base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 448 |
+
base_model.model.model.layers.19.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 449 |
+
base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 450 |
+
base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 451 |
+
base_model.model.model.layers.19.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 452 |
+
base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 453 |
+
base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 454 |
+
base_model.model.model.layers.19.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 455 |
+
base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 456 |
+
base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 457 |
+
base_model.model.model.layers.19.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 458 |
+
base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 459 |
+
base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 460 |
+
base_model.model.model.layers.19.input_layernorm.weight torch.Size([4096]) False
|
| 461 |
+
base_model.model.model.layers.19.post_attention_layernorm.weight torch.Size([4096]) False
|
| 462 |
+
base_model.model.model.layers.20.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 463 |
+
base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 464 |
+
base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 465 |
+
base_model.model.model.layers.20.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 466 |
+
base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 467 |
+
base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 468 |
+
base_model.model.model.layers.20.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 469 |
+
base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 470 |
+
base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 471 |
+
base_model.model.model.layers.20.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 472 |
+
base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 473 |
+
base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 474 |
+
base_model.model.model.layers.20.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 475 |
+
base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 476 |
+
base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 477 |
+
base_model.model.model.layers.20.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 478 |
+
base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 479 |
+
base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 480 |
+
base_model.model.model.layers.20.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 481 |
+
base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 482 |
+
base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 483 |
+
base_model.model.model.layers.20.input_layernorm.weight torch.Size([4096]) False
|
| 484 |
+
base_model.model.model.layers.20.post_attention_layernorm.weight torch.Size([4096]) False
|
| 485 |
+
base_model.model.model.layers.21.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 486 |
+
base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 487 |
+
base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 488 |
+
base_model.model.model.layers.21.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 489 |
+
base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 490 |
+
base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 491 |
+
base_model.model.model.layers.21.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 492 |
+
base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 493 |
+
base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 494 |
+
base_model.model.model.layers.21.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 495 |
+
base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 496 |
+
base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 497 |
+
base_model.model.model.layers.21.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 498 |
+
base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 499 |
+
base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 500 |
+
base_model.model.model.layers.21.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 501 |
+
base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 502 |
+
base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 503 |
+
base_model.model.model.layers.21.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 504 |
+
base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 505 |
+
base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 506 |
+
base_model.model.model.layers.21.input_layernorm.weight torch.Size([4096]) False
|
| 507 |
+
base_model.model.model.layers.21.post_attention_layernorm.weight torch.Size([4096]) False
|
| 508 |
+
base_model.model.model.layers.22.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 509 |
+
base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 510 |
+
base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 511 |
+
base_model.model.model.layers.22.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 512 |
+
base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 513 |
+
base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 514 |
+
base_model.model.model.layers.22.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 515 |
+
base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 516 |
+
base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 517 |
+
base_model.model.model.layers.22.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 518 |
+
base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 519 |
+
base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 520 |
+
base_model.model.model.layers.22.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 521 |
+
base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 522 |
+
base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 523 |
+
base_model.model.model.layers.22.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 524 |
+
base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 525 |
+
base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 526 |
+
base_model.model.model.layers.22.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 527 |
+
base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 528 |
+
base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 529 |
+
base_model.model.model.layers.22.input_layernorm.weight torch.Size([4096]) False
|
| 530 |
+
base_model.model.model.layers.22.post_attention_layernorm.weight torch.Size([4096]) False
|
| 531 |
+
base_model.model.model.layers.23.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 532 |
+
base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 533 |
+
base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 534 |
+
base_model.model.model.layers.23.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 535 |
+
base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 536 |
+
base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 537 |
+
base_model.model.model.layers.23.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 538 |
+
base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 539 |
+
base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 540 |
+
base_model.model.model.layers.23.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 541 |
+
base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 542 |
+
base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 543 |
+
base_model.model.model.layers.23.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 544 |
+
base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 545 |
+
base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 546 |
+
base_model.model.model.layers.23.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 547 |
+
base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 548 |
+
base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 549 |
+
base_model.model.model.layers.23.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 550 |
+
base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 551 |
+
base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 552 |
+
base_model.model.model.layers.23.input_layernorm.weight torch.Size([4096]) False
|
| 553 |
+
base_model.model.model.layers.23.post_attention_layernorm.weight torch.Size([4096]) False
|
| 554 |
+
base_model.model.model.layers.24.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 555 |
+
base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 556 |
+
base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 557 |
+
base_model.model.model.layers.24.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 558 |
+
base_model.model.model.layers.24.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 559 |
+
base_model.model.model.layers.24.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 560 |
+
base_model.model.model.layers.24.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 561 |
+
base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 562 |
+
base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 563 |
+
base_model.model.model.layers.24.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 564 |
+
base_model.model.model.layers.24.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 565 |
+
base_model.model.model.layers.24.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 566 |
+
base_model.model.model.layers.24.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 567 |
+
base_model.model.model.layers.24.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 568 |
+
base_model.model.model.layers.24.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 569 |
+
base_model.model.model.layers.24.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 570 |
+
base_model.model.model.layers.24.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 571 |
+
base_model.model.model.layers.24.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 572 |
+
base_model.model.model.layers.24.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 573 |
+
base_model.model.model.layers.24.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 574 |
+
base_model.model.model.layers.24.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 575 |
+
base_model.model.model.layers.24.input_layernorm.weight torch.Size([4096]) False
|
| 576 |
+
base_model.model.model.layers.24.post_attention_layernorm.weight torch.Size([4096]) False
|
| 577 |
+
base_model.model.model.layers.25.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 578 |
+
base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 579 |
+
base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 580 |
+
base_model.model.model.layers.25.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 581 |
+
base_model.model.model.layers.25.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 582 |
+
base_model.model.model.layers.25.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 583 |
+
base_model.model.model.layers.25.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 584 |
+
base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 585 |
+
base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 586 |
+
base_model.model.model.layers.25.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 587 |
+
base_model.model.model.layers.25.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 588 |
+
base_model.model.model.layers.25.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 589 |
+
base_model.model.model.layers.25.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 590 |
+
base_model.model.model.layers.25.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 591 |
+
base_model.model.model.layers.25.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 592 |
+
base_model.model.model.layers.25.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 593 |
+
base_model.model.model.layers.25.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 594 |
+
base_model.model.model.layers.25.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 595 |
+
base_model.model.model.layers.25.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 596 |
+
base_model.model.model.layers.25.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 597 |
+
base_model.model.model.layers.25.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 598 |
+
base_model.model.model.layers.25.input_layernorm.weight torch.Size([4096]) False
|
| 599 |
+
base_model.model.model.layers.25.post_attention_layernorm.weight torch.Size([4096]) False
|
| 600 |
+
base_model.model.model.layers.26.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 601 |
+
base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 602 |
+
base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 603 |
+
base_model.model.model.layers.26.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 604 |
+
base_model.model.model.layers.26.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 605 |
+
base_model.model.model.layers.26.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 606 |
+
base_model.model.model.layers.26.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 607 |
+
base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 608 |
+
base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 609 |
+
base_model.model.model.layers.26.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 610 |
+
base_model.model.model.layers.26.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 611 |
+
base_model.model.model.layers.26.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 612 |
+
base_model.model.model.layers.26.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 613 |
+
base_model.model.model.layers.26.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 614 |
+
base_model.model.model.layers.26.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 615 |
+
base_model.model.model.layers.26.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 616 |
+
base_model.model.model.layers.26.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 617 |
+
base_model.model.model.layers.26.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 618 |
+
base_model.model.model.layers.26.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 619 |
+
base_model.model.model.layers.26.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 620 |
+
base_model.model.model.layers.26.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 621 |
+
base_model.model.model.layers.26.input_layernorm.weight torch.Size([4096]) False
|
| 622 |
+
base_model.model.model.layers.26.post_attention_layernorm.weight torch.Size([4096]) False
|
| 623 |
+
base_model.model.model.layers.27.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 624 |
+
base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 625 |
+
base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 626 |
+
base_model.model.model.layers.27.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 627 |
+
base_model.model.model.layers.27.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 628 |
+
base_model.model.model.layers.27.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 629 |
+
base_model.model.model.layers.27.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 630 |
+
base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 631 |
+
base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 632 |
+
base_model.model.model.layers.27.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 633 |
+
base_model.model.model.layers.27.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 634 |
+
base_model.model.model.layers.27.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 635 |
+
base_model.model.model.layers.27.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 636 |
+
base_model.model.model.layers.27.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 637 |
+
base_model.model.model.layers.27.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 638 |
+
base_model.model.model.layers.27.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 639 |
+
base_model.model.model.layers.27.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 640 |
+
base_model.model.model.layers.27.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 641 |
+
base_model.model.model.layers.27.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 642 |
+
base_model.model.model.layers.27.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 643 |
+
base_model.model.model.layers.27.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 644 |
+
base_model.model.model.layers.27.input_layernorm.weight torch.Size([4096]) False
|
| 645 |
+
base_model.model.model.layers.27.post_attention_layernorm.weight torch.Size([4096]) False
|
| 646 |
+
base_model.model.model.layers.28.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 647 |
+
base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 648 |
+
base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 649 |
+
base_model.model.model.layers.28.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 650 |
+
base_model.model.model.layers.28.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 651 |
+
base_model.model.model.layers.28.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 652 |
+
base_model.model.model.layers.28.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 653 |
+
base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 654 |
+
base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 655 |
+
base_model.model.model.layers.28.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 656 |
+
base_model.model.model.layers.28.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 657 |
+
base_model.model.model.layers.28.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 658 |
+
base_model.model.model.layers.28.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 659 |
+
base_model.model.model.layers.28.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 660 |
+
base_model.model.model.layers.28.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 661 |
+
base_model.model.model.layers.28.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 662 |
+
base_model.model.model.layers.28.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 663 |
+
base_model.model.model.layers.28.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 664 |
+
base_model.model.model.layers.28.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 665 |
+
base_model.model.model.layers.28.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 666 |
+
base_model.model.model.layers.28.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 667 |
+
base_model.model.model.layers.28.input_layernorm.weight torch.Size([4096]) False
|
| 668 |
+
base_model.model.model.layers.28.post_attention_layernorm.weight torch.Size([4096]) False
|
| 669 |
+
base_model.model.model.layers.29.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 670 |
+
base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 671 |
+
base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 672 |
+
base_model.model.model.layers.29.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 673 |
+
base_model.model.model.layers.29.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 674 |
+
base_model.model.model.layers.29.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 675 |
+
base_model.model.model.layers.29.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 676 |
+
base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 677 |
+
base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 678 |
+
base_model.model.model.layers.29.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 679 |
+
base_model.model.model.layers.29.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 680 |
+
base_model.model.model.layers.29.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 681 |
+
base_model.model.model.layers.29.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 682 |
+
base_model.model.model.layers.29.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 683 |
+
base_model.model.model.layers.29.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 684 |
+
base_model.model.model.layers.29.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 685 |
+
base_model.model.model.layers.29.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 686 |
+
base_model.model.model.layers.29.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 687 |
+
base_model.model.model.layers.29.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 688 |
+
base_model.model.model.layers.29.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 689 |
+
base_model.model.model.layers.29.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 690 |
+
base_model.model.model.layers.29.input_layernorm.weight torch.Size([4096]) False
|
| 691 |
+
base_model.model.model.layers.29.post_attention_layernorm.weight torch.Size([4096]) False
|
| 692 |
+
base_model.model.model.layers.30.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 693 |
+
base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 694 |
+
base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 695 |
+
base_model.model.model.layers.30.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 696 |
+
base_model.model.model.layers.30.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 697 |
+
base_model.model.model.layers.30.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 698 |
+
base_model.model.model.layers.30.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 699 |
+
base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 700 |
+
base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 701 |
+
base_model.model.model.layers.30.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 702 |
+
base_model.model.model.layers.30.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 703 |
+
base_model.model.model.layers.30.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 704 |
+
base_model.model.model.layers.30.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 705 |
+
base_model.model.model.layers.30.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 706 |
+
base_model.model.model.layers.30.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 707 |
+
base_model.model.model.layers.30.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 708 |
+
base_model.model.model.layers.30.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 709 |
+
base_model.model.model.layers.30.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 710 |
+
base_model.model.model.layers.30.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 711 |
+
base_model.model.model.layers.30.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 712 |
+
base_model.model.model.layers.30.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 713 |
+
base_model.model.model.layers.30.input_layernorm.weight torch.Size([4096]) False
|
| 714 |
+
base_model.model.model.layers.30.post_attention_layernorm.weight torch.Size([4096]) False
|
| 715 |
+
base_model.model.model.layers.31.self_attn.q_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 716 |
+
base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 717 |
+
base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 718 |
+
base_model.model.model.layers.31.self_attn.k_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 719 |
+
base_model.model.model.layers.31.self_attn.k_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 720 |
+
base_model.model.model.layers.31.self_attn.k_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 721 |
+
base_model.model.model.layers.31.self_attn.v_proj.base_layer.weight torch.Size([1024, 4096]) False
|
| 722 |
+
base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 723 |
+
base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.weight torch.Size([1024, 64]) False
|
| 724 |
+
base_model.model.model.layers.31.self_attn.o_proj.base_layer.weight torch.Size([4096, 4096]) False
|
| 725 |
+
base_model.model.model.layers.31.self_attn.o_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 726 |
+
base_model.model.model.layers.31.self_attn.o_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 727 |
+
base_model.model.model.layers.31.mlp.gate_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 728 |
+
base_model.model.model.layers.31.mlp.gate_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 729 |
+
base_model.model.model.layers.31.mlp.gate_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 730 |
+
base_model.model.model.layers.31.mlp.up_proj.base_layer.weight torch.Size([14336, 4096]) False
|
| 731 |
+
base_model.model.model.layers.31.mlp.up_proj.lora_A.default.weight torch.Size([64, 4096]) False
|
| 732 |
+
base_model.model.model.layers.31.mlp.up_proj.lora_B.default.weight torch.Size([14336, 64]) False
|
| 733 |
+
base_model.model.model.layers.31.mlp.down_proj.base_layer.weight torch.Size([4096, 14336]) False
|
| 734 |
+
base_model.model.model.layers.31.mlp.down_proj.lora_A.default.weight torch.Size([64, 14336]) False
|
| 735 |
+
base_model.model.model.layers.31.mlp.down_proj.lora_B.default.weight torch.Size([4096, 64]) False
|
| 736 |
+
base_model.model.model.layers.31.input_layernorm.weight torch.Size([4096]) False
|
| 737 |
+
base_model.model.model.layers.31.post_attention_layernorm.weight torch.Size([4096]) False
|
| 738 |
+
base_model.model.model.norm.weight torch.Size([4096]) False
|
| 739 |
+
base_model.model.model.vision_clip_lmm_projector.0.weight torch.Size([4096, 1024]) True
|
| 740 |
+
base_model.model.model.vision_clip_lmm_projector.0.bias torch.Size([4096]) True
|
| 741 |
+
base_model.model.model.vision_clip_lmm_projector.2.weight torch.Size([4096, 4096]) True
|
| 742 |
+
base_model.model.model.vision_clip_lmm_projector.2.bias torch.Size([4096]) True
|
| 743 |
+
base_model.model.lm_head.weight torch.Size([32000, 4096]) False
|
non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:956aaa1108300c5753ebe9b02ec008d5961bb3ff113f6c3fe3afa07cc9991e95
|
| 3 |
+
size 41961255
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|