Upload folder using huggingface_hub
Browse files- README.md +329 -0
- added_tokens.json +24 -0
- config.json +40 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- output.safetensors +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +207 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
5 |
+
tags:
|
6 |
+
- axolotl
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
|
10 |
+
- PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
|
11 |
+
- PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
|
12 |
+
- PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
|
13 |
+
- PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
|
14 |
+
- PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
|
15 |
+
- PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
|
16 |
+
- PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
|
17 |
+
- PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
|
18 |
+
- PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
|
19 |
+
model-index:
|
20 |
+
- name: Qwen2.5-QwQ-RP-Draft-v0.2-1.5B-LoRA-WS
|
21 |
+
results: []
|
22 |
+
---
|
23 |
+
|
24 |
+

|
25 |
+
|
26 |
+
Note: More models will be added to this comparison.
|
27 |
+
|
28 |
+

|
29 |
+
|
30 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
31 |
+
should probably proofread and complete it, then remove this comment. -->
|
32 |
+
|
33 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
34 |
+
<details><summary>See axolotl config</summary>
|
35 |
+
|
36 |
+
axolotl version: `0.8.0.dev0`
|
37 |
+
```yaml
|
38 |
+
mlflow_tracking_uri: http://127.0.0.1:7860
|
39 |
+
mlflow_experiment_name: Qwen2.5-QwQ-RP-Draft-v0.2-1.5B-LoRA
|
40 |
+
|
41 |
+
# Hugging Face saving config
|
42 |
+
hub_model_id: BeaverAI/Qwen2.5-QwQ-RP-Draft-v0.2-1.5B-LoRA-WS
|
43 |
+
hub_strategy: every_save
|
44 |
+
|
45 |
+
# Model checkpointing config
|
46 |
+
output_dir: ./Outputs/Qwen2.5-QwQ-RP-Draft-v0.2-1.5B-LoRA
|
47 |
+
resume_from_checkpoint:
|
48 |
+
save_steps: 10
|
49 |
+
save_safetensors: true
|
50 |
+
save_total_limit: 3
|
51 |
+
save_only_model: false
|
52 |
+
|
53 |
+
# Model architecture config
|
54 |
+
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
55 |
+
model_type: AutoModelForCausalLM
|
56 |
+
tokenizer_type: AutoTokenizer
|
57 |
+
|
58 |
+
# Mixed precision training config
|
59 |
+
bf16: true
|
60 |
+
fp16: false
|
61 |
+
tf32: false
|
62 |
+
|
63 |
+
# Model loading config
|
64 |
+
load_in_8bit: false
|
65 |
+
load_in_4bit: false
|
66 |
+
strict: false
|
67 |
+
|
68 |
+
# Sequence config
|
69 |
+
sequence_len: 8192
|
70 |
+
min_sample_len: 256
|
71 |
+
sample_packing: true
|
72 |
+
eval_sample_packing: false
|
73 |
+
pad_to_sequence_len: true
|
74 |
+
train_on_inputs: false
|
75 |
+
group_by_length: false
|
76 |
+
|
77 |
+
# LoRA adapter config
|
78 |
+
adapter: lora
|
79 |
+
lora_model_dir:
|
80 |
+
lora_r: 128
|
81 |
+
lora_alpha: 128
|
82 |
+
lora_dropout: 0.125
|
83 |
+
peft_layers_to_transform:
|
84 |
+
peft_use_dora:
|
85 |
+
peft_use_rslora:
|
86 |
+
peft_layer_replication:
|
87 |
+
lora_target_modules:
|
88 |
+
- gate_proj
|
89 |
+
- down_proj
|
90 |
+
- up_proj
|
91 |
+
- q_proj
|
92 |
+
- v_proj
|
93 |
+
- k_proj
|
94 |
+
- o_proj
|
95 |
+
lora_modules_to_save:
|
96 |
+
|
97 |
+
# Fix uninitialized tokens (such as <|start_header_id|> on the base L3 models)
|
98 |
+
fix_untrained_tokens:
|
99 |
+
|
100 |
+
# Dataset config
|
101 |
+
# https://github.com/xzuyn/axolotl/blob/prompt_formats/src/axolotl/prompt_strategies/customchatml-regex-last-only.py
|
102 |
+
datasets:
|
103 |
+
- path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
|
104 |
+
split: train
|
105 |
+
type: customchatml-regex-last-only
|
106 |
+
- path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
|
107 |
+
split: train
|
108 |
+
type: customchatml-regex-last-only
|
109 |
+
- path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
|
110 |
+
split: train
|
111 |
+
type: customchatml-regex-last-only
|
112 |
+
- path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
|
113 |
+
split: train
|
114 |
+
type: customchatml-regex-last-only
|
115 |
+
- path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
|
116 |
+
split: train
|
117 |
+
type: customchatml-regex-last-only
|
118 |
+
- path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
|
119 |
+
split: train
|
120 |
+
type: customchatml-regex-last-only
|
121 |
+
- path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
|
122 |
+
split: train
|
123 |
+
type: customchatml-regex-last-only
|
124 |
+
- path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
|
125 |
+
split: train
|
126 |
+
type: customchatml-regex-last-only
|
127 |
+
- path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
|
128 |
+
split: train
|
129 |
+
type: customchatml-regex-last-only
|
130 |
+
- path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
|
131 |
+
split: train
|
132 |
+
type: customchatml-regex-last-only
|
133 |
+
test_datasets:
|
134 |
+
- path: PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled
|
135 |
+
split: test
|
136 |
+
type: customchatml-regex-last-only
|
137 |
+
- path: PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled
|
138 |
+
split: test
|
139 |
+
type: customchatml-regex-last-only
|
140 |
+
- path: PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled
|
141 |
+
split: test
|
142 |
+
type: customchatml-regex-last-only
|
143 |
+
- path: PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled
|
144 |
+
split: test
|
145 |
+
type: customchatml-regex-last-only
|
146 |
+
- path: PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled
|
147 |
+
split: test
|
148 |
+
type: customchatml-regex-last-only
|
149 |
+
- path: PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled
|
150 |
+
split: test
|
151 |
+
type: customchatml-regex-last-only
|
152 |
+
- path: PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled
|
153 |
+
split: test
|
154 |
+
type: customchatml-regex-last-only
|
155 |
+
- path: PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled
|
156 |
+
split: test
|
157 |
+
type: customchatml-regex-last-only
|
158 |
+
- path: PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled
|
159 |
+
split: test
|
160 |
+
type: customchatml-regex-last-only
|
161 |
+
- path: PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled
|
162 |
+
split: test
|
163 |
+
type: customchatml-regex-last-only
|
164 |
+
val_set_size: 0
|
165 |
+
eval_strategy: steps
|
166 |
+
eval_steps: 10
|
167 |
+
dataset_prepared_path: ./00-Tokenized-Datasets/Qwen2.5-QwQ-Draft-v0.2-1.5B-customchatml-regex-last-only
|
168 |
+
shuffle_merged_datasets: true
|
169 |
+
dataset_processes:
|
170 |
+
|
171 |
+
# Training hyperparameters
|
172 |
+
num_epochs: 2
|
173 |
+
gradient_accumulation_steps: 1
|
174 |
+
micro_batch_size: 16 # x4 GPUs = 64
|
175 |
+
eval_batch_size: 16 # x4 GPUs = 64
|
176 |
+
warmup_steps: 0
|
177 |
+
optimizer: came_pytorch
|
178 |
+
optim_args:
|
179 |
+
optim_target_modules:
|
180 |
+
lr_scheduler: rex
|
181 |
+
learning_rate: 2e-5
|
182 |
+
cosine_min_lr_ratio:
|
183 |
+
loraplus_lr_ratio:
|
184 |
+
loraplus_lr_embedding:
|
185 |
+
weight_decay: 0.1
|
186 |
+
max_grad_norm: 1
|
187 |
+
logging_steps: 1
|
188 |
+
|
189 |
+
# Model optimization
|
190 |
+
gradient_checkpointing: unsloth
|
191 |
+
flash_attention: true
|
192 |
+
plugins:
|
193 |
+
- axolotl.integrations.liger.LigerPlugin
|
194 |
+
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
195 |
+
cut_cross_entropy: true
|
196 |
+
liger_rope: true
|
197 |
+
liger_rms_norm: true
|
198 |
+
liger_layer_norm: true
|
199 |
+
liger_glu_activation: true
|
200 |
+
liger_cross_entropy: false
|
201 |
+
liger_fused_linear_cross_entropy: false
|
202 |
+
lora_mlp_kernel: false
|
203 |
+
lora_qkv_kernel: false
|
204 |
+
lora_o_kernel: false
|
205 |
+
|
206 |
+
# DeepSpeed
|
207 |
+
deepspeed: deepspeed_configs/zero3_bf16.json
|
208 |
+
|
209 |
+
# Garbage Collection
|
210 |
+
gc_steps: 1
|
211 |
+
|
212 |
+
# Debug config
|
213 |
+
debug: true
|
214 |
+
seed: 42
|
215 |
+
|
216 |
+
# Token config
|
217 |
+
special_tokens:
|
218 |
+
eos_token: "<|endoftext|>"
|
219 |
+
pad_token: "<|endoftext|>"
|
220 |
+
tokens:
|
221 |
+
|
222 |
+
```
|
223 |
+
|
224 |
+
</details><br>
|
225 |
+
|
226 |
+
# Qwen2.5-QwQ-RP-Draft-v0.2-1.5B-LoRA-WS
|
227 |
+
|
228 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the PJMixers-Dev/allura-org_gryphe-sonnet-3.5-charcards-names-added-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/anthracite-org_c2_logs_32k_llama3_qwen2_v1.3-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/grimulkan_aicg-logs-augmented-system-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/grimulkan_jannie-log-augmented-system-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/grimulkan_PIPPA-augmented-dedup-system-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/lemonilia_LimaRP-Only-NonSus-Simple-CustomShareGPT-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/MinervaAI_Aesir-Preview-Anon-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/NyxKrage_chub-logs-sharegpt-longest-CustomShareGPT-qwq-all-aphrodite-Shuffled, the PJMixers-Dev/PocketDoc_Dans-Prosemaxx-Cowriter-XL-8192-shrunk-l3-qwq-all-aphrodite-Shuffled and the PJMixers-Dev/PocketDoc_Dans-Personamaxx-Rainy-qwq-all-aphrodite-Shuffled datasets.
|
229 |
+
It achieves the following results on the evaluation set:
|
230 |
+
- Loss: 1.7920
|
231 |
+
|
232 |
+
## Model description
|
233 |
+
|
234 |
+
More information needed
|
235 |
+
|
236 |
+
## Intended uses & limitations
|
237 |
+
|
238 |
+
More information needed
|
239 |
+
|
240 |
+
## Training and evaluation data
|
241 |
+
|
242 |
+
More information needed
|
243 |
+
|
244 |
+
## Training procedure
|
245 |
+
|
246 |
+
### Training hyperparameters
|
247 |
+
|
248 |
+
The following hyperparameters were used during training:
|
249 |
+
- learning_rate: 2e-05
|
250 |
+
- train_batch_size: 16
|
251 |
+
- eval_batch_size: 16
|
252 |
+
- seed: 42
|
253 |
+
- distributed_type: multi-GPU
|
254 |
+
- num_devices: 4
|
255 |
+
- total_train_batch_size: 64
|
256 |
+
- total_eval_batch_size: 64
|
257 |
+
- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
258 |
+
- lr_scheduler_type: cosine
|
259 |
+
- num_epochs: 2.0
|
260 |
+
|
261 |
+
### Training results
|
262 |
+
|
263 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
264 |
+
|:-------------:|:------:|:----:|:---------------:|
|
265 |
+
| 2.7253 | 0.0036 | 1 | 2.6463 |
|
266 |
+
| 2.4339 | 0.0362 | 10 | 2.3864 |
|
267 |
+
| 2.2821 | 0.0725 | 20 | 2.2571 |
|
268 |
+
| 2.207 | 0.1087 | 30 | 2.1771 |
|
269 |
+
| 2.1213 | 0.1449 | 40 | 2.1225 |
|
270 |
+
| 2.0926 | 0.1812 | 50 | 2.0870 |
|
271 |
+
| 2.0274 | 0.2174 | 60 | 2.0585 |
|
272 |
+
| 2.0292 | 0.2536 | 70 | 2.0338 |
|
273 |
+
| 2.0057 | 0.2899 | 80 | 2.0148 |
|
274 |
+
| 1.9841 | 0.3261 | 90 | 1.9975 |
|
275 |
+
| 1.9639 | 0.3623 | 100 | 1.9812 |
|
276 |
+
| 1.9303 | 0.3986 | 110 | 1.9688 |
|
277 |
+
| 1.9527 | 0.4348 | 120 | 1.9569 |
|
278 |
+
| 1.9389 | 0.4710 | 130 | 1.9459 |
|
279 |
+
| 1.9008 | 0.5072 | 140 | 1.9352 |
|
280 |
+
| 1.8996 | 0.5435 | 150 | 1.9259 |
|
281 |
+
| 1.8849 | 0.5797 | 160 | 1.9171 |
|
282 |
+
| 1.8793 | 0.6159 | 170 | 1.9105 |
|
283 |
+
| 1.8748 | 0.6522 | 180 | 1.9019 |
|
284 |
+
| 1.8697 | 0.6884 | 190 | 1.8959 |
|
285 |
+
| 1.8777 | 0.7246 | 200 | 1.8892 |
|
286 |
+
| 1.8731 | 0.7609 | 210 | 1.8833 |
|
287 |
+
| 1.8358 | 0.7971 | 220 | 1.8772 |
|
288 |
+
| 1.8483 | 0.8333 | 230 | 1.8729 |
|
289 |
+
| 1.8567 | 0.8696 | 240 | 1.8679 |
|
290 |
+
| 1.8461 | 0.9058 | 250 | 1.8632 |
|
291 |
+
| 1.8436 | 0.9420 | 260 | 1.8591 |
|
292 |
+
| 1.7992 | 0.9783 | 270 | 1.8545 |
|
293 |
+
| 1.7925 | 1.0145 | 280 | 1.8510 |
|
294 |
+
| 1.814 | 1.0507 | 290 | 1.8461 |
|
295 |
+
| 1.8249 | 1.0870 | 300 | 1.8431 |
|
296 |
+
| 1.7889 | 1.1232 | 310 | 1.8391 |
|
297 |
+
| 1.8116 | 1.1594 | 320 | 1.8367 |
|
298 |
+
| 1.7895 | 1.1957 | 330 | 1.8339 |
|
299 |
+
| 1.7951 | 1.2319 | 340 | 1.8300 |
|
300 |
+
| 1.7831 | 1.2681 | 350 | 1.8272 |
|
301 |
+
| 1.7919 | 1.3043 | 360 | 1.8250 |
|
302 |
+
| 1.7755 | 1.3406 | 370 | 1.8224 |
|
303 |
+
| 1.7895 | 1.3768 | 380 | 1.8209 |
|
304 |
+
| 1.7806 | 1.4130 | 390 | 1.8184 |
|
305 |
+
| 1.7808 | 1.4493 | 400 | 1.8156 |
|
306 |
+
| 1.7771 | 1.4855 | 410 | 1.8136 |
|
307 |
+
| 1.7636 | 1.5217 | 420 | 1.8118 |
|
308 |
+
| 1.7719 | 1.5580 | 430 | 1.8098 |
|
309 |
+
| 1.7716 | 1.5942 | 440 | 1.8074 |
|
310 |
+
| 1.7917 | 1.6304 | 450 | 1.8056 |
|
311 |
+
| 1.784 | 1.6667 | 460 | 1.8035 |
|
312 |
+
| 1.7846 | 1.7029 | 470 | 1.8019 |
|
313 |
+
| 1.7485 | 1.7391 | 480 | 1.8002 |
|
314 |
+
| 1.7381 | 1.7754 | 490 | 1.7987 |
|
315 |
+
| 1.764 | 1.8116 | 500 | 1.7972 |
|
316 |
+
| 1.744 | 1.8478 | 510 | 1.7964 |
|
317 |
+
| 1.7673 | 1.8841 | 520 | 1.7948 |
|
318 |
+
| 1.7926 | 1.9203 | 530 | 1.7935 |
|
319 |
+
| 1.7843 | 1.9565 | 540 | 1.7926 |
|
320 |
+
| 1.7689 | 1.9928 | 550 | 1.7920 |
|
321 |
+
|
322 |
+
|
323 |
+
### Framework versions
|
324 |
+
|
325 |
+
- PEFT 0.14.0
|
326 |
+
- Transformers 4.49.0
|
327 |
+
- Pytorch 2.6.0+cu124
|
328 |
+
- Datasets 3.2.0
|
329 |
+
- Tokenizers 0.21.1
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1536,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8960,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 21,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 2,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": 32768,
|
23 |
+
"tie_word_embeddings": true,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.50.0.dev0",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 151936,
|
29 |
+
"quantization_config": {
|
30 |
+
"quant_method": "exl2",
|
31 |
+
"version": "0.2.8",
|
32 |
+
"bits": 4.0,
|
33 |
+
"head_bits": 8,
|
34 |
+
"calibration": {
|
35 |
+
"rows": 115,
|
36 |
+
"length": 2048,
|
37 |
+
"dataset": "(default)"
|
38 |
+
}
|
39 |
+
}
|
40 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.50.0.dev0"
|
14 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebfa9be4c1920b8fb5959318d9aff90aaf5aaff9d71556e436823c22e03e50b4
|
3 |
+
size 1356437582
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"split_special_tokens": false,
|
205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
206 |
+
"unk_token": null
|
207 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|