Upload folder using huggingface_hub
Browse files- Master-Yi-9B.webp +0 -0
- README.md +483 -0
- config.json +40 -0
- generation_config.json +7 -0
- model.safetensors.index.json +442 -0
- output-00001-of-00002.safetensors +3 -0
- output-00002-of-00002.safetensors +3 -0
- special_tokens_map.json +39 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
Master-Yi-9B.webp
ADDED
|
README.md
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
## Model Description
|
| 6 |
+
|
| 7 |
+
Master is a collection of LLMs trained using human-collected seed questions and regenerate the answers with a mixture of high performance Open-source LLMs.
|
| 8 |
+
|
| 9 |
+
**Master-Yi-9B** is trained using the ORPO technique. The model shows strong abilities in reasoning on coding and math questions.
|
| 10 |
+
|
| 11 |
+
**Quantized Version**: [Here](https://huggingface.co/qnguyen3/Master-Yi-9B-GGUF)
|
| 12 |
+
|
| 13 |
+
**Master-Yi-9B-Vision**: **Coming Soon**
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
## Prompt Template
|
| 19 |
+
|
| 20 |
+
```
|
| 21 |
+
<|im_start|>system
|
| 22 |
+
You are a helpful AI assistant.<|im_end|>
|
| 23 |
+
<|im_start|>user
|
| 24 |
+
What is the meaning of life?<|im_end|>
|
| 25 |
+
<|im_start|>assistant
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
## Examples
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
## Inference Code
|
| 35 |
+
|
| 36 |
+
```python
|
| 37 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 38 |
+
import torch
|
| 39 |
+
device = "cuda" # the device to load the model onto
|
| 40 |
+
|
| 41 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 42 |
+
"vilm/VinaLlama2-14B",
|
| 43 |
+
torch_dtype='auto',
|
| 44 |
+
device_map="auto"
|
| 45 |
+
)
|
| 46 |
+
tokenizer = AutoTokenizer.from_pretrained("vilm/VinaLlama2-14B")
|
| 47 |
+
|
| 48 |
+
prompt = "What is the mearning of life?"
|
| 49 |
+
messages = [
|
| 50 |
+
{"role": "system", "content": "You are a helpful AI assistant."},
|
| 51 |
+
{"role": "user", "content": prompt}
|
| 52 |
+
]
|
| 53 |
+
text = tokenizer.apply_chat_template(
|
| 54 |
+
messages,
|
| 55 |
+
tokenize=False,
|
| 56 |
+
add_generation_prompt=True
|
| 57 |
+
)
|
| 58 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(device)
|
| 59 |
+
|
| 60 |
+
generated_ids = model.generate(
|
| 61 |
+
model_inputs.input_ids,
|
| 62 |
+
max_new_tokens=1024,
|
| 63 |
+
eos_token_id=tokenizer.eos_token_id,
|
| 64 |
+
temperature=0.25,
|
| 65 |
+
)
|
| 66 |
+
generated_ids = [
|
| 67 |
+
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
| 68 |
+
]
|
| 69 |
+
|
| 70 |
+
response = tokenizer.batch_decode(generated_ids)[0]
|
| 71 |
+
print(response)
|
| 72 |
+
```
|
| 73 |
+
|
| 74 |
+
## Benchmarks
|
| 75 |
+
|
| 76 |
+
### Nous Benchmark:
|
| 77 |
+
|
| 78 |
+
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|
| 79 |
+
|---------------------------------------------------|------:|------:|---------:|-------:|------:|
|
| 80 |
+
|[Master-Yi-9B](https://huggingface.co/qnguyen3/Master-Yi-9B)| 43.55| 71.48| 48.54| 41.43| 51.25|
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### AGIEval
|
| 84 |
+
```
|
| 85 |
+
| Task |Version| Metric |Value| |Stderr|
|
| 86 |
+
|------------------------------|------:|--------|----:|---|-----:|
|
| 87 |
+
|agieval_aqua_rat | 0|acc |35.83|± | 3.01|
|
| 88 |
+
| | |acc_norm|31.89|± | 2.93|
|
| 89 |
+
|agieval_logiqa_en | 0|acc |38.25|± | 1.91|
|
| 90 |
+
| | |acc_norm|37.79|± | 1.90|
|
| 91 |
+
|agieval_lsat_ar | 0|acc |23.04|± | 2.78|
|
| 92 |
+
| | |acc_norm|20.43|± | 2.66|
|
| 93 |
+
|agieval_lsat_lr | 0|acc |48.04|± | 2.21|
|
| 94 |
+
| | |acc_norm|42.75|± | 2.19|
|
| 95 |
+
|agieval_lsat_rc | 0|acc |61.34|± | 2.97|
|
| 96 |
+
| | |acc_norm|52.79|± | 3.05|
|
| 97 |
+
|agieval_sat_en | 0|acc |79.13|± | 2.84|
|
| 98 |
+
| | |acc_norm|72.33|± | 3.12|
|
| 99 |
+
|agieval_sat_en_without_passage| 0|acc |44.17|± | 3.47|
|
| 100 |
+
| | |acc_norm|42.72|± | 3.45|
|
| 101 |
+
|agieval_sat_math | 0|acc |52.27|± | 3.38|
|
| 102 |
+
| | |acc_norm|47.73|± | 3.38|
|
| 103 |
+
|
| 104 |
+
Average: 43.55%
|
| 105 |
+
```
|
| 106 |
+
|
| 107 |
+
### GPT4All
|
| 108 |
+
```
|
| 109 |
+
| Task |Version| Metric |Value| |Stderr|
|
| 110 |
+
|-------------|------:|--------|----:|---|-----:|
|
| 111 |
+
|arc_challenge| 0|acc |54.95|± | 1.45|
|
| 112 |
+
| | |acc_norm|58.70|± | 1.44|
|
| 113 |
+
|arc_easy | 0|acc |82.28|± | 0.78|
|
| 114 |
+
| | |acc_norm|81.10|± | 0.80|
|
| 115 |
+
|boolq | 1|acc |86.15|± | 0.60|
|
| 116 |
+
|hellaswag | 0|acc |59.16|± | 0.49|
|
| 117 |
+
| | |acc_norm|77.53|± | 0.42|
|
| 118 |
+
|openbookqa | 0|acc |37.40|± | 2.17|
|
| 119 |
+
| | |acc_norm|44.00|± | 2.22|
|
| 120 |
+
|piqa | 0|acc |79.00|± | 0.95|
|
| 121 |
+
| | |acc_norm|80.25|± | 0.93|
|
| 122 |
+
|winogrande | 0|acc |72.61|± | 1.25|
|
| 123 |
+
|
| 124 |
+
Average: 71.48%
|
| 125 |
+
```
|
| 126 |
+
|
| 127 |
+
### TruthfulQA
|
| 128 |
+
```
|
| 129 |
+
| Task |Version|Metric|Value| |Stderr|
|
| 130 |
+
|-------------|------:|------|----:|---|-----:|
|
| 131 |
+
|truthfulqa_mc| 1|mc1 |33.05|± | 1.65|
|
| 132 |
+
| | |mc2 |48.54|± | 1.54|
|
| 133 |
+
|
| 134 |
+
Average: 48.54%
|
| 135 |
+
```
|
| 136 |
+
|
| 137 |
+
### Bigbench
|
| 138 |
+
```
|
| 139 |
+
| Task |Version| Metric |Value| |Stderr|
|
| 140 |
+
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|
| 141 |
+
|bigbench_causal_judgement | 0|multiple_choice_grade|54.74|± | 3.62|
|
| 142 |
+
|bigbench_date_understanding | 0|multiple_choice_grade|68.02|± | 2.43|
|
| 143 |
+
|bigbench_disambiguation_qa | 0|multiple_choice_grade|40.31|± | 3.06|
|
| 144 |
+
|bigbench_geometric_shapes | 0|multiple_choice_grade|30.36|± | 2.43|
|
| 145 |
+
| | |exact_str_match | 2.23|± | 0.78|
|
| 146 |
+
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|26.00|± | 1.96|
|
| 147 |
+
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|20.71|± | 1.53|
|
| 148 |
+
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|44.00|± | 2.87|
|
| 149 |
+
|bigbench_movie_recommendation | 0|multiple_choice_grade|35.00|± | 2.14|
|
| 150 |
+
|bigbench_navigate | 0|multiple_choice_grade|58.40|± | 1.56|
|
| 151 |
+
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|61.80|± | 1.09|
|
| 152 |
+
|bigbench_ruin_names | 0|multiple_choice_grade|42.41|± | 2.34|
|
| 153 |
+
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|31.56|± | 1.47|
|
| 154 |
+
|bigbench_snarks | 0|multiple_choice_grade|55.25|± | 3.71|
|
| 155 |
+
|bigbench_sports_understanding | 0|multiple_choice_grade|69.37|± | 1.47|
|
| 156 |
+
|bigbench_temporal_sequences | 0|multiple_choice_grade|27.70|± | 1.42|
|
| 157 |
+
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|21.36|± | 1.16|
|
| 158 |
+
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|14.69|± | 0.85|
|
| 159 |
+
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|44.00|± | 2.87|
|
| 160 |
+
|
| 161 |
+
Average: 41.43%
|
| 162 |
+
```
|
| 163 |
+
|
| 164 |
+
**Average score**: 51.25%
|
| 165 |
+
|
| 166 |
+
|
| 167 |
+
### OpenLLM Benchmark:
|
| 168 |
+
|
| 169 |
+
| Model |ARC |HellaSwag|MMLU |TruthfulQA|Winogrande|GSM8K|Average|
|
| 170 |
+
|---------------------------------------------------|---:|--------:|----:|---------:|---------:|----:|------:|
|
| 171 |
+
|[Master-Yi-9B](https://huggingface.co/qnguyen3/Master-Yi-9B)|61.6| 79.89|69.95| 48.59| 77.35|67.48| 67.48|
|
| 172 |
+
|
| 173 |
+
### ARC
|
| 174 |
+
```
|
| 175 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 176 |
+
|-------------|------:|--------------------|-------------|---|------|
|
| 177 |
+
|arc_challenge| 1|acc,none | 0.59| | |
|
| 178 |
+
| | |acc_stderr,none | 0.01| | |
|
| 179 |
+
| | |acc_norm,none | 0.62| | |
|
| 180 |
+
| | |acc_norm_stderr,none| 0.01| | |
|
| 181 |
+
| | |alias |arc_challenge| | |
|
| 182 |
+
|
| 183 |
+
Average: 61.6%
|
| 184 |
+
```
|
| 185 |
+
|
| 186 |
+
### HellaSwag
|
| 187 |
+
```
|
| 188 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 189 |
+
|---------|------:|--------------------|---------|---|------|
|
| 190 |
+
|hellaswag| 1|acc,none | 0.61| | |
|
| 191 |
+
| | |acc_stderr,none | 0| | |
|
| 192 |
+
| | |acc_norm,none | 0.80| | |
|
| 193 |
+
| | |acc_norm_stderr,none| 0| | |
|
| 194 |
+
| | |alias |hellaswag| | |
|
| 195 |
+
|
| 196 |
+
Average: 79.89%
|
| 197 |
+
```
|
| 198 |
+
|
| 199 |
+
### MMLU
|
| 200 |
+
```
|
| 201 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 202 |
+
|----------------------------------------|-------|---------------|---------------------------------------|---|------|
|
| 203 |
+
|mmlu |N/A |acc,none | 0.7| | |
|
| 204 |
+
| | |acc_stderr,none| 0| | |
|
| 205 |
+
| | |alias |mmlu | | |
|
| 206 |
+
|mmlu_abstract_algebra | 0|alias | - abstract_algebra | | |
|
| 207 |
+
| | |acc,none |0.46 | | |
|
| 208 |
+
| | |acc_stderr,none|0.05 | | |
|
| 209 |
+
|mmlu_anatomy | 0|alias | - anatomy | | |
|
| 210 |
+
| | |acc,none |0.64 | | |
|
| 211 |
+
| | |acc_stderr,none|0.04 | | |
|
| 212 |
+
|mmlu_astronomy | 0|alias | - astronomy | | |
|
| 213 |
+
| | |acc,none |0.77 | | |
|
| 214 |
+
| | |acc_stderr,none|0.03 | | |
|
| 215 |
+
|mmlu_business_ethics | 0|alias | - business_ethics | | |
|
| 216 |
+
| | |acc,none |0.76 | | |
|
| 217 |
+
| | |acc_stderr,none|0.04 | | |
|
| 218 |
+
|mmlu_clinical_knowledge | 0|alias | - clinical_knowledge | | |
|
| 219 |
+
| | |acc,none |0.71 | | |
|
| 220 |
+
| | |acc_stderr,none|0.03 | | |
|
| 221 |
+
|mmlu_college_biology | 0|alias | - college_biology | | |
|
| 222 |
+
| | |acc,none |0.82 | | |
|
| 223 |
+
| | |acc_stderr,none|0.03 | | |
|
| 224 |
+
|mmlu_college_chemistry | 0|alias | - college_chemistry | | |
|
| 225 |
+
| | |acc,none |0.52 | | |
|
| 226 |
+
| | |acc_stderr,none|0.05 | | |
|
| 227 |
+
|mmlu_college_computer_science | 0|alias | - college_computer_science | | |
|
| 228 |
+
| | |acc,none |0.56 | | |
|
| 229 |
+
| | |acc_stderr,none|0.05 | | |
|
| 230 |
+
|mmlu_college_mathematics | 0|alias | - college_mathematics | | |
|
| 231 |
+
| | |acc,none |0.44 | | |
|
| 232 |
+
| | |acc_stderr,none|0.05 | | |
|
| 233 |
+
|mmlu_college_medicine | 0|alias | - college_medicine | | |
|
| 234 |
+
| | |acc,none |0.72 | | |
|
| 235 |
+
| | |acc_stderr,none|0.03 | | |
|
| 236 |
+
|mmlu_college_physics | 0|alias | - college_physics | | |
|
| 237 |
+
| | |acc,none |0.45 | | |
|
| 238 |
+
| | |acc_stderr,none|0.05 | | |
|
| 239 |
+
|mmlu_computer_security | 0|alias | - computer_security | | |
|
| 240 |
+
| | |acc,none |0.81 | | |
|
| 241 |
+
| | |acc_stderr,none|0.04 | | |
|
| 242 |
+
|mmlu_conceptual_physics | 0|alias | - conceptual_physics | | |
|
| 243 |
+
| | |acc,none |0.74 | | |
|
| 244 |
+
| | |acc_stderr,none|0.03 | | |
|
| 245 |
+
|mmlu_econometrics | 0|alias | - econometrics | | |
|
| 246 |
+
| | |acc,none |0.65 | | |
|
| 247 |
+
| | |acc_stderr,none|0.04 | | |
|
| 248 |
+
|mmlu_electrical_engineering | 0|alias | - electrical_engineering | | |
|
| 249 |
+
| | |acc,none |0.72 | | |
|
| 250 |
+
| | |acc_stderr,none|0.04 | | |
|
| 251 |
+
|mmlu_elementary_mathematics | 0|alias | - elementary_mathematics | | |
|
| 252 |
+
| | |acc,none |0.62 | | |
|
| 253 |
+
| | |acc_stderr,none|0.02 | | |
|
| 254 |
+
|mmlu_formal_logic | 0|alias | - formal_logic | | |
|
| 255 |
+
| | |acc,none |0.57 | | |
|
| 256 |
+
| | |acc_stderr,none|0.04 | | |
|
| 257 |
+
|mmlu_global_facts | 0|alias | - global_facts | | |
|
| 258 |
+
| | |acc,none |0.46 | | |
|
| 259 |
+
| | |acc_stderr,none|0.05 | | |
|
| 260 |
+
|mmlu_high_school_biology | 0|alias | - high_school_biology | | |
|
| 261 |
+
| | |acc,none |0.86 | | |
|
| 262 |
+
| | |acc_stderr,none|0.02 | | |
|
| 263 |
+
|mmlu_high_school_chemistry | 0|alias | - high_school_chemistry | | |
|
| 264 |
+
| | |acc,none |0.67 | | |
|
| 265 |
+
| | |acc_stderr,none|0.03 | | |
|
| 266 |
+
|mmlu_high_school_computer_science | 0|alias | - high_school_computer_science | | |
|
| 267 |
+
| | |acc,none |0.84 | | |
|
| 268 |
+
| | |acc_stderr,none|0.04 | | |
|
| 269 |
+
|mmlu_high_school_european_history | 0|alias | - high_school_european_history | | |
|
| 270 |
+
| | |acc,none |0.82 | | |
|
| 271 |
+
| | |acc_stderr,none|0.03 | | |
|
| 272 |
+
|mmlu_high_school_geography | 0|alias | - high_school_geography | | |
|
| 273 |
+
| | |acc,none |0.86 | | |
|
| 274 |
+
| | |acc_stderr,none|0.02 | | |
|
| 275 |
+
|mmlu_high_school_government_and_politics| 0|alias | - high_school_government_and_politics| | |
|
| 276 |
+
| | |acc,none |0.90 | | |
|
| 277 |
+
| | |acc_stderr,none|0.02 | | |
|
| 278 |
+
|mmlu_high_school_macroeconomics | 0|alias | - high_school_macroeconomics | | |
|
| 279 |
+
| | |acc,none |0.75 | | |
|
| 280 |
+
| | |acc_stderr,none|0.02 | | |
|
| 281 |
+
|mmlu_high_school_mathematics | 0|alias | - high_school_mathematics | | |
|
| 282 |
+
| | |acc,none |0.43 | | |
|
| 283 |
+
| | |acc_stderr,none|0.03 | | |
|
| 284 |
+
|mmlu_high_school_microeconomics | 0|alias | - high_school_microeconomics | | |
|
| 285 |
+
| | |acc,none |0.86 | | |
|
| 286 |
+
| | |acc_stderr,none|0.02 | | |
|
| 287 |
+
|mmlu_high_school_physics | 0|alias | - high_school_physics | | |
|
| 288 |
+
| | |acc,none |0.45 | | |
|
| 289 |
+
| | |acc_stderr,none|0.04 | | |
|
| 290 |
+
|mmlu_high_school_psychology | 0|alias | - high_school_psychology | | |
|
| 291 |
+
| | |acc,none |0.87 | | |
|
| 292 |
+
| | |acc_stderr,none|0.01 | | |
|
| 293 |
+
|mmlu_high_school_statistics | 0|alias | - high_school_statistics | | |
|
| 294 |
+
| | |acc,none |0.68 | | |
|
| 295 |
+
| | |acc_stderr,none|0.03 | | |
|
| 296 |
+
|mmlu_high_school_us_history | 0|alias | - high_school_us_history | | |
|
| 297 |
+
| | |acc,none |0.85 | | |
|
| 298 |
+
| | |acc_stderr,none|0.02 | | |
|
| 299 |
+
|mmlu_high_school_world_history | 0|alias | - high_school_world_history | | |
|
| 300 |
+
| | |acc,none |0.85 | | |
|
| 301 |
+
| | |acc_stderr,none|0.02 | | |
|
| 302 |
+
|mmlu_human_aging | 0|alias | - human_aging | | |
|
| 303 |
+
| | |acc,none |0.76 | | |
|
| 304 |
+
| | |acc_stderr,none|0.03 | | |
|
| 305 |
+
|mmlu_human_sexuality | 0|alias | - human_sexuality | | |
|
| 306 |
+
| | |acc,none |0.78 | | |
|
| 307 |
+
| | |acc_stderr,none|0.04 | | |
|
| 308 |
+
|mmlu_humanities |N/A |alias | - humanities | | |
|
| 309 |
+
| | |acc,none |0.63 | | |
|
| 310 |
+
| | |acc_stderr,none|0.01 | | |
|
| 311 |
+
|mmlu_international_law | 0|alias | - international_law | | |
|
| 312 |
+
| | |acc,none |0.79 | | |
|
| 313 |
+
| | |acc_stderr,none|0.04 | | |
|
| 314 |
+
|mmlu_jurisprudence | 0|alias | - jurisprudence | | |
|
| 315 |
+
| | |acc,none |0.79 | | |
|
| 316 |
+
| | |acc_stderr,none|0.04 | | |
|
| 317 |
+
|mmlu_logical_fallacies | 0|alias | - logical_fallacies | | |
|
| 318 |
+
| | |acc,none |0.80 | | |
|
| 319 |
+
| | |acc_stderr,none|0.03 | | |
|
| 320 |
+
|mmlu_machine_learning | 0|alias | - machine_learning | | |
|
| 321 |
+
| | |acc,none |0.52 | | |
|
| 322 |
+
| | |acc_stderr,none|0.05 | | |
|
| 323 |
+
|mmlu_management | 0|alias | - management | | |
|
| 324 |
+
| | |acc,none |0.83 | | |
|
| 325 |
+
| | |acc_stderr,none|0.04 | | |
|
| 326 |
+
|mmlu_marketing | 0|alias | - marketing | | |
|
| 327 |
+
| | |acc,none |0.89 | | |
|
| 328 |
+
| | |acc_stderr,none|0.02 | | |
|
| 329 |
+
|mmlu_medical_genetics | 0|alias | - medical_genetics | | |
|
| 330 |
+
| | |acc,none |0.78 | | |
|
| 331 |
+
| | |acc_stderr,none|0.04 | | |
|
| 332 |
+
|mmlu_miscellaneous | 0|alias | - miscellaneous | | |
|
| 333 |
+
| | |acc,none |0.85 | | |
|
| 334 |
+
| | |acc_stderr,none|0.01 | | |
|
| 335 |
+
|mmlu_moral_disputes | 0|alias | - moral_disputes | | |
|
| 336 |
+
| | |acc,none |0.75 | | |
|
| 337 |
+
| | |acc_stderr,none|0.02 | | |
|
| 338 |
+
|mmlu_moral_scenarios | 0|alias | - moral_scenarios | | |
|
| 339 |
+
| | |acc,none |0.48 | | |
|
| 340 |
+
| | |acc_stderr,none|0.02 | | |
|
| 341 |
+
|mmlu_nutrition | 0|alias | - nutrition | | |
|
| 342 |
+
| | |acc,none |0.77 | | |
|
| 343 |
+
| | |acc_stderr,none|0.02 | | |
|
| 344 |
+
|mmlu_other |N/A |alias | - other | | |
|
| 345 |
+
| | |acc,none |0.75 | | |
|
| 346 |
+
| | |acc_stderr,none|0.01 | | |
|
| 347 |
+
|mmlu_philosophy | 0|alias | - philosophy | | |
|
| 348 |
+
| | |acc,none |0.78 | | |
|
| 349 |
+
| | |acc_stderr,none|0.02 | | |
|
| 350 |
+
|mmlu_prehistory | 0|alias | - prehistory | | |
|
| 351 |
+
| | |acc,none |0.77 | | |
|
| 352 |
+
| | |acc_stderr,none|0.02 | | |
|
| 353 |
+
|mmlu_professional_accounting | 0|alias | - professional_accounting | | |
|
| 354 |
+
| | |acc,none |0.57 | | |
|
| 355 |
+
| | |acc_stderr,none|0.03 | | |
|
| 356 |
+
|mmlu_professional_law | 0|alias | - professional_law | | |
|
| 357 |
+
| | |acc,none |0.50 | | |
|
| 358 |
+
| | |acc_stderr,none|0.01 | | |
|
| 359 |
+
|mmlu_professional_medicine | 0|alias | - professional_medicine | | |
|
| 360 |
+
| | |acc,none |0.71 | | |
|
| 361 |
+
| | |acc_stderr,none|0.03 | | |
|
| 362 |
+
|mmlu_professional_psychology | 0|alias | - professional_psychology | | |
|
| 363 |
+
| | |acc,none |0.73 | | |
|
| 364 |
+
| | |acc_stderr,none|0.02 | | |
|
| 365 |
+
|mmlu_public_relations | 0|alias | - public_relations | | |
|
| 366 |
+
| | |acc,none |0.76 | | |
|
| 367 |
+
| | |acc_stderr,none|0.04 | | |
|
| 368 |
+
|mmlu_security_studies | 0|alias | - security_studies | | |
|
| 369 |
+
| | |acc,none |0.78 | | |
|
| 370 |
+
| | |acc_stderr,none|0.03 | | |
|
| 371 |
+
|mmlu_social_sciences |N/A |alias | - social_sciences | | |
|
| 372 |
+
| | |acc,none |0.81 | | |
|
| 373 |
+
| | |acc_stderr,none|0.01 | | |
|
| 374 |
+
|mmlu_sociology | 0|alias | - sociology | | |
|
| 375 |
+
| | |acc,none |0.86 | | |
|
| 376 |
+
| | |acc_stderr,none|0.02 | | |
|
| 377 |
+
|mmlu_stem |N/A |alias | - stem | | |
|
| 378 |
+
| | |acc,none |0.65 | | |
|
| 379 |
+
| | |acc_stderr,none|0.01 | | |
|
| 380 |
+
|mmlu_us_foreign_policy | 0|alias | - us_foreign_policy | | |
|
| 381 |
+
| | |acc,none |0.92 | | |
|
| 382 |
+
| | |acc_stderr,none|0.03 | | |
|
| 383 |
+
|mmlu_virology | 0|alias | - virology | | |
|
| 384 |
+
| | |acc,none |0.58 | | |
|
| 385 |
+
| | |acc_stderr,none|0.04 | | |
|
| 386 |
+
|mmlu_world_religions | 0|alias | - world_religions | | |
|
| 387 |
+
| | |acc,none |0.82 | | |
|
| 388 |
+
| | |acc_stderr,none|0.03 | | |
|
| 389 |
+
|
| 390 |
+
Average: 69.95%
|
| 391 |
+
```
|
| 392 |
+
|
| 393 |
+
### TruthfulQA
|
| 394 |
+
```
|
| 395 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 396 |
+
|--------------|-------|-----------------------|-----------------|---|------|
|
| 397 |
+
|truthfulqa |N/A |bleu_acc,none | 0.45| | |
|
| 398 |
+
| | |bleu_acc_stderr,none | 0.02| | |
|
| 399 |
+
| | |rouge1_acc,none | 0.45| | |
|
| 400 |
+
| | |rouge1_acc_stderr,none | 0.02| | |
|
| 401 |
+
| | |rouge2_diff,none | 0.92| | |
|
| 402 |
+
| | |rouge2_diff_stderr,none| 1.07| | |
|
| 403 |
+
| | |bleu_max,none | 23.77| | |
|
| 404 |
+
| | |bleu_max_stderr,none | 0.81| | |
|
| 405 |
+
| | |rouge2_acc,none | 0.38| | |
|
| 406 |
+
| | |rouge2_acc_stderr,none | 0.02| | |
|
| 407 |
+
| | |acc,none | 0.41| | |
|
| 408 |
+
| | |acc_stderr,none | 0.01| | |
|
| 409 |
+
| | |rougeL_diff,none | 1.57| | |
|
| 410 |
+
| | |rougeL_diff_stderr,none| 0.93| | |
|
| 411 |
+
| | |rougeL_acc,none | 0.46| | |
|
| 412 |
+
| | |rougeL_acc_stderr,none | 0.02| | |
|
| 413 |
+
| | |bleu_diff,none | 1.38| | |
|
| 414 |
+
| | |bleu_diff_stderr,none | 0.75| | |
|
| 415 |
+
| | |rouge2_max,none | 33.01| | |
|
| 416 |
+
| | |rouge2_max_stderr,none | 1.05| | |
|
| 417 |
+
| | |rouge1_diff,none | 1.72| | |
|
| 418 |
+
| | |rouge1_diff_stderr,none| 0.92| | |
|
| 419 |
+
| | |rougeL_max,none | 45.25| | |
|
| 420 |
+
| | |rougeL_max_stderr,none | 0.92| | |
|
| 421 |
+
| | |rouge1_max,none | 48.29| | |
|
| 422 |
+
| | |rouge1_max_stderr,none | 0.90| | |
|
| 423 |
+
| | |alias |truthfulqa | | |
|
| 424 |
+
|truthfulqa_gen| 3|bleu_max,none | 23.77| | |
|
| 425 |
+
| | |bleu_max_stderr,none | 0.81| | |
|
| 426 |
+
| | |bleu_acc,none | 0.45| | |
|
| 427 |
+
| | |bleu_acc_stderr,none | 0.02| | |
|
| 428 |
+
| | |bleu_diff,none | 1.38| | |
|
| 429 |
+
| | |bleu_diff_stderr,none | 0.75| | |
|
| 430 |
+
| | |rouge1_max,none | 48.29| | |
|
| 431 |
+
| | |rouge1_max_stderr,none | 0.90| | |
|
| 432 |
+
| | |rouge1_acc,none | 0.45| | |
|
| 433 |
+
| | |rouge1_acc_stderr,none | 0.02| | |
|
| 434 |
+
| | |rouge1_diff,none | 1.72| | |
|
| 435 |
+
| | |rouge1_diff_stderr,none| 0.92| | |
|
| 436 |
+
| | |rouge2_max,none | 33.01| | |
|
| 437 |
+
| | |rouge2_max_stderr,none | 1.05| | |
|
| 438 |
+
| | |rouge2_acc,none | 0.38| | |
|
| 439 |
+
| | |rouge2_acc_stderr,none | 0.02| | |
|
| 440 |
+
| | |rouge2_diff,none | 0.92| | |
|
| 441 |
+
| | |rouge2_diff_stderr,none| 1.07| | |
|
| 442 |
+
| | |rougeL_max,none | 45.25| | |
|
| 443 |
+
| | |rougeL_max_stderr,none | 0.92| | |
|
| 444 |
+
| | |rougeL_acc,none | 0.46| | |
|
| 445 |
+
| | |rougeL_acc_stderr,none | 0.02| | |
|
| 446 |
+
| | |rougeL_diff,none | 1.57| | |
|
| 447 |
+
| | |rougeL_diff_stderr,none| 0.93| | |
|
| 448 |
+
| | |alias | - truthfulqa_gen| | |
|
| 449 |
+
|truthfulqa_mc1| 2|acc,none | 0.33| | |
|
| 450 |
+
| | |acc_stderr,none | 0.02| | |
|
| 451 |
+
| | |alias | - truthfulqa_mc1| | |
|
| 452 |
+
|truthfulqa_mc2| 2|acc,none | 0.49| | |
|
| 453 |
+
| | |acc_stderr,none | 0.02| | |
|
| 454 |
+
| | |alias | - truthfulqa_mc2| | |
|
| 455 |
+
|
| 456 |
+
Average: 48.59%
|
| 457 |
+
```
|
| 458 |
+
|
| 459 |
+
### Winogrande
|
| 460 |
+
```
|
| 461 |
+
| Task |Version| Metric | Value | |Stderr|
|
| 462 |
+
|----------|------:|---------------|----------|---|------|
|
| 463 |
+
|winogrande| 1|acc,none | 0.77| | |
|
| 464 |
+
| | |acc_stderr,none| 0.01| | |
|
| 465 |
+
| | |alias |winogrande| | |
|
| 466 |
+
|
| 467 |
+
Average: 77.35%
|
| 468 |
+
```
|
| 469 |
+
|
| 470 |
+
### GSM8K
|
| 471 |
+
```
|
| 472 |
+
|Task |Version| Metric |Value| |Stderr|
|
| 473 |
+
|-----|------:|-----------------------------------|-----|---|------|
|
| 474 |
+
|gsm8k| 3|exact_match,strict-match | 0.67| | |
|
| 475 |
+
| | |exact_match_stderr,strict-match | 0.01| | |
|
| 476 |
+
| | |exact_match,flexible-extract | 0.68| | |
|
| 477 |
+
| | |exact_match_stderr,flexible-extract| 0.01| | |
|
| 478 |
+
| | |alias |gsm8k| | |
|
| 479 |
+
|
| 480 |
+
Average: 67.48%
|
| 481 |
+
```
|
| 482 |
+
|
| 483 |
+
**Average score**: 67.48%
|
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "01-ai/Yi-1.5-9B",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 7,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"max_position_embeddings": 4096,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 48,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"rms_norm_eps": 1e-06,
|
| 22 |
+
"rope_scaling": null,
|
| 23 |
+
"rope_theta": 5000000.0,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.40.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 64000,
|
| 29 |
+
"quantization_config": {
|
| 30 |
+
"quant_method": "exl2",
|
| 31 |
+
"version": "0.0.21",
|
| 32 |
+
"bits": 8.0,
|
| 33 |
+
"head_bits": 8,
|
| 34 |
+
"calibration": {
|
| 35 |
+
"rows": 100,
|
| 36 |
+
"length": 2048,
|
| 37 |
+
"dataset": "(default)"
|
| 38 |
+
}
|
| 39 |
+
}
|
| 40 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 7,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.40.1"
|
| 7 |
+
}
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,442 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 17658814464
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00005-of-00005.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 242 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 243 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 245 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 251 |
+
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 252 |
+
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 254 |
+
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 260 |
+
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 261 |
+
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 263 |
+
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 269 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 270 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 272 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 278 |
+
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 279 |
+
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 281 |
+
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 287 |
+
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 288 |
+
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 290 |
+
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 296 |
+
"model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 297 |
+
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 299 |
+
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 305 |
+
"model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 306 |
+
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 308 |
+
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 314 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 315 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 317 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 323 |
+
"model.layers.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 324 |
+
"model.layers.40.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 325 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 326 |
+
"model.layers.40.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 327 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 328 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 329 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 330 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 331 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 332 |
+
"model.layers.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 333 |
+
"model.layers.41.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 334 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 335 |
+
"model.layers.41.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 336 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 337 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 338 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 339 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 340 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 341 |
+
"model.layers.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 342 |
+
"model.layers.42.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 343 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 344 |
+
"model.layers.42.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 345 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 346 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 347 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 348 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 349 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 350 |
+
"model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 351 |
+
"model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 352 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 353 |
+
"model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 354 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 355 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 356 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 357 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 358 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 359 |
+
"model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 360 |
+
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 361 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 362 |
+
"model.layers.44.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 363 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 364 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 365 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 366 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 367 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 368 |
+
"model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 369 |
+
"model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 370 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 371 |
+
"model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 372 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 373 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 374 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 375 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 376 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 377 |
+
"model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 378 |
+
"model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 379 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 380 |
+
"model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 381 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 382 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 383 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 384 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 385 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 386 |
+
"model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 387 |
+
"model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 388 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 389 |
+
"model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 390 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 391 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 392 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 393 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 394 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 395 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 396 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 397 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 398 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 399 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 400 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 401 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 402 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 403 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 404 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 405 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 406 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 407 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 408 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 409 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 410 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 411 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 412 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 413 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 414 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 415 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 416 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 417 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 418 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 419 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 420 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 421 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 422 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 423 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 424 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 425 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 426 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 427 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 428 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 429 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 430 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 431 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 432 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 433 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 434 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 435 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 436 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 437 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 440 |
+
"model.norm.weight": "model-00005-of-00005.safetensors"
|
| 441 |
+
}
|
| 442 |
+
}
|
output-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:261cc68b66eb6f6193c0404bae08c693fd4c25e2c464db112bf96ad46dbabf75
|
| 3 |
+
size 8358041640
|
output-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71f51b480e584f4863ca4cc485e236f52b3a9ff8d03103514812736ab58a5510
|
| 3 |
+
size 262144096
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|im_start|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|startoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|im_end|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": {
|
| 26 |
+
"content": "<unk>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"unk_token": {
|
| 33 |
+
"content": "<unk>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
}
|
| 39 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
| 3 |
+
size 1033105
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<|startoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<|endoftext|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"6": {
|
| 30 |
+
"content": "<|im_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"7": {
|
| 38 |
+
"content": "<|im_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
}
|
| 45 |
+
},
|
| 46 |
+
"additional_special_tokens": [
|
| 47 |
+
"<|im_start|>"
|
| 48 |
+
],
|
| 49 |
+
"bos_token": "<|startoftext|>",
|
| 50 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
|
| 51 |
+
"clean_up_tokenization_spaces": false,
|
| 52 |
+
"eos_token": "<|im_end|>",
|
| 53 |
+
"legacy": true,
|
| 54 |
+
"model_max_length": 4096,
|
| 55 |
+
"pad_token": "<unk>",
|
| 56 |
+
"padding_side": "left",
|
| 57 |
+
"sp_model_kwargs": {},
|
| 58 |
+
"split_special_tokens": false,
|
| 59 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 60 |
+
"unk_token": "<unk>",
|
| 61 |
+
"use_default_system_prompt": false
|
| 62 |
+
}
|