Upload folder using huggingface_hub
Browse files- README.md +41 -0
- adapter_config.json +47 -0
- adapter_model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- 05466d56569b55db_train_data.json
|
| 7 |
+
base_model: defog/sqlcoder-7b-2
|
| 8 |
+
model-index:
|
| 9 |
+
- name: JacksonBrune/87230327-b73a-4d52-a711-20a7e1f47c73
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# JacksonBrune/87230327-b73a-4d52-a711-20a7e1f47c73
|
| 18 |
+
|
| 19 |
+
This model was trained from scratch on the /root/tmp/05466d56569b55db_train_data.json dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1037
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
### Framework versions
|
| 36 |
+
|
| 37 |
+
- PEFT 0.15.0
|
| 38 |
+
- Transformers 4.50.3
|
| 39 |
+
- Pytorch 2.5.1+cu124
|
| 40 |
+
- Datasets 3.5.0
|
| 41 |
+
- Tokenizers 0.21.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "defog/sqlcoder-7b-2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": {
|
| 8 |
+
"adjust_scaling_factors": true,
|
| 9 |
+
"label_mask_value": -100,
|
| 10 |
+
"rho": 2.0,
|
| 11 |
+
"tau": 0.99,
|
| 12 |
+
"use_label_mask": true,
|
| 13 |
+
"whiten": false
|
| 14 |
+
},
|
| 15 |
+
"exclude_modules": null,
|
| 16 |
+
"fan_in_fan_out": null,
|
| 17 |
+
"inference_mode": true,
|
| 18 |
+
"init_lora_weights": "eva",
|
| 19 |
+
"layer_replication": null,
|
| 20 |
+
"layers_pattern": null,
|
| 21 |
+
"layers_to_transform": null,
|
| 22 |
+
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 256,
|
| 24 |
+
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0.05,
|
| 26 |
+
"megatron_config": null,
|
| 27 |
+
"megatron_core": "megatron.core",
|
| 28 |
+
"modules_to_save": null,
|
| 29 |
+
"peft_type": "LORA",
|
| 30 |
+
"r": 128,
|
| 31 |
+
"rank_pattern": {},
|
| 32 |
+
"revision": null,
|
| 33 |
+
"target_modules": [
|
| 34 |
+
"(?:language_model.)?model.layers.[\\d]+.(mlp|cross_attn|self_attn).(up|down|gate|q|k|v|o)_proj",
|
| 35 |
+
"gate_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"q_proj",
|
| 40 |
+
"o_proj",
|
| 41 |
+
"up_proj"
|
| 42 |
+
],
|
| 43 |
+
"task_type": "CAUSAL_LM",
|
| 44 |
+
"trainable_token_indices": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_rslora": false
|
| 47 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6be6f698d008927596126dfbbcc9095b4b56443c87d507154df5a679c98849c1
|
| 3 |
+
size 639692768
|