Upload folder using huggingface_hub
Browse files- README.md +233 -0
- bench-coven.txt +130 -0
- bench-mistral.txt +128 -0
- config.json +31 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +50 -0
README.md
ADDED
|
@@ -0,0 +1,233 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- text-generation
|
| 7 |
+
- large-language-model
|
| 8 |
+
- orpo
|
| 9 |
+
|
| 10 |
+
base_model:
|
| 11 |
+
- mistralai/Mistral-7B-Instruct-v0.2
|
| 12 |
+
model-index:
|
| 13 |
+
- name: Coven 7B 128K ORPO
|
| 14 |
+
description: "Coven 7B 128K ORPO is a derivative of Mistral-7B-Instruct-v0.2, fine-tuned to perform specialized tasks involving deeper understanding and reasoning over context. This model exhibits strong capabilities in both general language understanding and task-specific challenges."
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
type: text-generation
|
| 18 |
+
name: Winogrande Challenge
|
| 19 |
+
dataset:
|
| 20 |
+
name: Winogrande
|
| 21 |
+
type: winogrande_xl
|
| 22 |
+
split: test
|
| 23 |
+
args:
|
| 24 |
+
num_few_shot: 5
|
| 25 |
+
metrics:
|
| 26 |
+
- type: accuracy
|
| 27 |
+
value: 77.82
|
| 28 |
+
name: accuracy
|
| 29 |
+
- task:
|
| 30 |
+
type: text-generation
|
| 31 |
+
name: TruthfulQA Generation
|
| 32 |
+
dataset:
|
| 33 |
+
name: TruthfulQA
|
| 34 |
+
type: truthful_qa
|
| 35 |
+
config: multiple_choice
|
| 36 |
+
split: validation
|
| 37 |
+
args:
|
| 38 |
+
num_few_shot: 0
|
| 39 |
+
metrics:
|
| 40 |
+
- type: accuracy
|
| 41 |
+
value: 49.55
|
| 42 |
+
name: accuracy
|
| 43 |
+
- task:
|
| 44 |
+
type: text-generation
|
| 45 |
+
name: PIQA Problem Solving
|
| 46 |
+
dataset:
|
| 47 |
+
name: PIQA
|
| 48 |
+
type: piqa
|
| 49 |
+
split: validation
|
| 50 |
+
args:
|
| 51 |
+
num_few_shot: 5
|
| 52 |
+
metrics:
|
| 53 |
+
- type: accuracy
|
| 54 |
+
value: 82.05
|
| 55 |
+
name: accuracy
|
| 56 |
+
- task:
|
| 57 |
+
type: text-generation
|
| 58 |
+
name: OpenBookQA Facts
|
| 59 |
+
dataset:
|
| 60 |
+
name: OpenBookQA
|
| 61 |
+
type: openbookqa
|
| 62 |
+
split: test
|
| 63 |
+
args:
|
| 64 |
+
num_few_shot: 5
|
| 65 |
+
metrics:
|
| 66 |
+
- type: accuracy
|
| 67 |
+
value: 34.60
|
| 68 |
+
name: accuracy
|
| 69 |
+
- task:
|
| 70 |
+
type: text-generation
|
| 71 |
+
name: MMLU Knowledge Test
|
| 72 |
+
dataset:
|
| 73 |
+
name: MMLU
|
| 74 |
+
type: mmlu
|
| 75 |
+
config: all
|
| 76 |
+
split: test
|
| 77 |
+
args:
|
| 78 |
+
num_few_shot: 5
|
| 79 |
+
metrics:
|
| 80 |
+
- type: accuracy
|
| 81 |
+
value: 63.00
|
| 82 |
+
name: accuracy
|
| 83 |
+
- task:
|
| 84 |
+
type: text-generation
|
| 85 |
+
name: Hellaswag Contextual Completions
|
| 86 |
+
dataset:
|
| 87 |
+
name: Hellaswag
|
| 88 |
+
type: hellaswag
|
| 89 |
+
split: validation
|
| 90 |
+
args:
|
| 91 |
+
num_few_shot: 10
|
| 92 |
+
metrics:
|
| 93 |
+
- type: accuracy
|
| 94 |
+
value: 65.37
|
| 95 |
+
name: accuracy
|
| 96 |
+
- task:
|
| 97 |
+
type: text-generation
|
| 98 |
+
name: GSM8k Mathematical Reasoning
|
| 99 |
+
dataset:
|
| 100 |
+
name: GSM8k
|
| 101 |
+
type: gsm8k
|
| 102 |
+
split: test
|
| 103 |
+
args:
|
| 104 |
+
num_few_shot: 5
|
| 105 |
+
metrics:
|
| 106 |
+
- type: accuracy
|
| 107 |
+
value: 72.18
|
| 108 |
+
name: exact match (strict)
|
| 109 |
+
- type: accuracy
|
| 110 |
+
value: 72.63
|
| 111 |
+
name: exact match (flexible)
|
| 112 |
+
- task:
|
| 113 |
+
type: text-generation
|
| 114 |
+
name: BoolQ Question Answering
|
| 115 |
+
dataset:
|
| 116 |
+
name: BoolQ
|
| 117 |
+
type: boolq
|
| 118 |
+
split: validation
|
| 119 |
+
args:
|
| 120 |
+
num_few_shot: 5
|
| 121 |
+
metrics:
|
| 122 |
+
- type: accuracy
|
| 123 |
+
value: 87.43
|
| 124 |
+
name: accuracy
|
| 125 |
+
- task:
|
| 126 |
+
type: text-generation
|
| 127 |
+
name: ARC Challenge
|
| 128 |
+
dataset:
|
| 129 |
+
name: ARC Challenge
|
| 130 |
+
type: ai2_arc
|
| 131 |
+
split: test
|
| 132 |
+
args:
|
| 133 |
+
num_few_shot: 25
|
| 134 |
+
metrics:
|
| 135 |
+
- type: accuracy
|
| 136 |
+
value: 59.64
|
| 137 |
+
name: accuracy
|
| 138 |
+
---
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
# 🧙 Coven 7B 128K ORPO
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
Coven 7B 128K is an improved iteration of Mistral-7B-Instruct-v0.2, refined to expand processing capabilities and refine language model preferences. This model includes a significantly increased context constraint of 128K tokens using the Yarn technique, which allows for more extensive data processing and understanding of complex language scenarios. In addition, the Coven 7B 128K ORPO 32K tokenization uses the innovative ORPO (Monolithic Preference Optimization without Reference Model) technology. ORPO simplifies the fine-tuning process by directly optimizing the odds ratio to distinguish between favorable and unfavorable generation styles, effectively improving model performance without the need for an additional preference alignment step.
|
| 147 |
+
|
| 148 |
+
|
| 149 |
+
### Eval
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
| Task | Model | Metric | Value | Change (%) |
|
| 153 |
+
|---------------------|-------------------------|-------------------|----------|------------------------------|
|
| 154 |
+
| Winogrande | Mistral-7B-Instruct-v0.2| Accuracy | 73.64% | - |
|
| 155 |
+
| | Coven 7B 128K ORPO | Accuracy | 77.82% | +5.67% |
|
| 156 |
+
| TruthfulQA | Mistral-7B-Instruct-v0.2| Accuracy | 59.54% | - |
|
| 157 |
+
| | Coven 7B 128K ORPO | Accuracy | 49.55% | -16.78% |
|
| 158 |
+
| PIQA | Mistral-7B-Instruct-v0.2| Accuracy | 80.03% | - |
|
| 159 |
+
| | Coven 7B 128K ORPO | Accuracy | 82.05% | +2.52% |
|
| 160 |
+
| OpenBookQA | Mistral-7B-Instruct-v0.2| Accuracy | 36.00% | - |
|
| 161 |
+
| | Coven 7B 128K ORPO | Accuracy | 34.60% | -3.89% |
|
| 162 |
+
| | Mistral-7B-Instruct-v0.2| Accuracy Normalized| 45.20% | - |
|
| 163 |
+
| | Coven 7B 128K ORPO | Accuracy Normalized| 48.00% | +6.19% |
|
| 164 |
+
| MMLU | Mistral-7B-Instruct-v0.2| Accuracy | 58.79% | - |
|
| 165 |
+
| | Coven 7B 128K ORPO | Accuracy | 63.00% | +7.16% |
|
| 166 |
+
| Hellaswag | Mistral-7B-Instruct-v0.2| Accuracy | 66.08% | - |
|
| 167 |
+
| | Coven 7B 128K ORPO | Accuracy | 65.37% | -1.08% |
|
| 168 |
+
| | Mistral-7B-Instruct-v0.2| Accuracy Normalized| 83.68% | - |
|
| 169 |
+
| | Coven 7B 128K ORPO | Accuracy Normalized| 84.29% | +0.73% |
|
| 170 |
+
| GSM8K (Strict) | Mistral-7B-Instruct-v0.2| Exact Match | 41.55% | - |
|
| 171 |
+
| | Coven 7B 128K ORPO | Exact Match | 72.18% | +73.65% |
|
| 172 |
+
| GSM8K (Flexible) | Mistral-7B-Instruct-v0.2| Exact Match | 41.93% | - |
|
| 173 |
+
| | Coven 7B 128K ORPO | Exact Match | 72.63% | +73.29% |
|
| 174 |
+
| BoolQ | Mistral-7B-Instruct-v0.2| Accuracy | 85.29% | - |
|
| 175 |
+
| | Coven 7B 128K ORPO | Accuracy | 87.43% | +2.51% |
|
| 176 |
+
| ARC Easy | Mistral-7B-Instruct-v0.2| Accuracy | 81.36% | - |
|
| 177 |
+
| | Coven 7B 128K ORPO | Accuracy | 85.02% | +4.50% |
|
| 178 |
+
| | Mistral-7B-Instruct-v0.2| Accuracy Normalized| 76.60% | - |
|
| 179 |
+
| | Coven 7B 128K ORPO | Accuracy Normalized| 82.95% | +8.29% |
|
| 180 |
+
| ARC Challenge | Mistral-7B-Instruct-v0.2| Accuracy | 54.35% | - |
|
| 181 |
+
| | Coven 7B 128K ORPO | Accuracy | 59.64% | +9.74% |
|
| 182 |
+
| | Mistral-7B-Instruct-v0.2| Accuracy Normalized| 55.80% | - |
|
| 183 |
+
| | Coven 7B 128K ORPO | Accuracy Normalized| 61.69% | +10.52% |
|
| 184 |
+
|
| 185 |
+
|
| 186 |
+
|
| 187 |
+
## Model Details
|
| 188 |
+
|
| 189 |
+
* **Model name**: Coven 7B 128K ORPO alpha
|
| 190 |
+
* **Fine-tuned by**: raidhon
|
| 191 |
+
* **Base model**: [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
|
| 192 |
+
* **Parameters**: 7B
|
| 193 |
+
* **Context**: 128K
|
| 194 |
+
* **Language(s)**: Multilingual
|
| 195 |
+
* **License**: Apache2.0
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
## 💻 Usage
|
| 199 |
+
|
| 200 |
+
```python
|
| 201 |
+
# Install transformers from source - only needed for versions <= v4.34
|
| 202 |
+
# pip install git+https://github.com/huggingface/transformers.git
|
| 203 |
+
# pip install accelerate
|
| 204 |
+
|
| 205 |
+
import torch
|
| 206 |
+
from transformers import pipeline
|
| 207 |
+
|
| 208 |
+
pipe = pipeline("text-generation", model="raidhon/coven_7b_128k_orpo_alpha", torch_dtype=torch.float16, device_map="auto")
|
| 209 |
+
|
| 210 |
+
messages = [
|
| 211 |
+
{
|
| 212 |
+
"role": "system",
|
| 213 |
+
"content": "You are a friendly chatbot who always responds in the style of a pirate",
|
| 214 |
+
},
|
| 215 |
+
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
| 216 |
+
]
|
| 217 |
+
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 218 |
+
outputs = pipe(prompt, max_new_tokens=4096, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
| 219 |
+
print(outputs[0]["generated_text"])
|
| 220 |
+
```
|
| 221 |
+
|
| 222 |
+
|
| 223 |
+
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
|
| 227 |
+
|
| 228 |
+
|
| 229 |
+
|
| 230 |
+
|
| 231 |
+
|
| 232 |
+
|
| 233 |
+
|
bench-coven.txt
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
raidhon/coven_7b_128k_orpo_alpha
|
| 2 |
+
|
| 3 |
+
| Tasks |Version| Filter |n-shot| Metric | Value | |Stderr|
|
| 4 |
+
|---------------------------------------|-------|----------------|-----:|-----------|------:|---|-----:|
|
| 5 |
+
|winogrande | 1|none | 0|acc | 0.7782|± |0.0117|
|
| 6 |
+
|truthfulqa |N/A |none | 0|rouge1_max |47.8575|± |0.8139|
|
| 7 |
+
| | |none | 0|bleu_max |21.9412|± |0.7280|
|
| 8 |
+
| | |none | 0|rouge2_max |32.7726|± |0.9228|
|
| 9 |
+
| | |none | 0|rougeL_diff|-1.4310|± |0.7806|
|
| 10 |
+
| | |none | 0|acc | 0.4955|± |0.0115|
|
| 11 |
+
| | |none | 0|bleu_diff |-0.2883|± |0.6228|
|
| 12 |
+
| | |none | 0|rouge2_acc | 0.3807|± |0.0170|
|
| 13 |
+
| | |none | 0|rougeL_max |44.1785|± |0.8274|
|
| 14 |
+
| | |none | 0|rougeL_acc | 0.4443|± |0.0174|
|
| 15 |
+
| | |none | 0|rouge2_diff|-1.5603|± |0.8950|
|
| 16 |
+
| | |none | 0|bleu_acc | 0.4321|± |0.0173|
|
| 17 |
+
| | |none | 0|rouge1_diff|-0.7276|± |0.7721|
|
| 18 |
+
| | |none | 0|rouge1_acc | 0.4774|± |0.0175|
|
| 19 |
+
| - truthfulqa_gen | 3|none | 0|bleu_max |21.9412|± |0.7280|
|
| 20 |
+
| | |none | 0|bleu_acc | 0.4321|± |0.0173|
|
| 21 |
+
| | |none | 0|bleu_diff |-0.2883|± |0.6228|
|
| 22 |
+
| | |none | 0|rouge1_max |47.8575|± |0.8139|
|
| 23 |
+
| | |none | 0|rouge1_acc | 0.4774|± |0.0175|
|
| 24 |
+
| | |none | 0|rouge1_diff|-0.7276|± |0.7721|
|
| 25 |
+
| | |none | 0|rouge2_max |32.7726|± |0.9228|
|
| 26 |
+
| | |none | 0|rouge2_acc | 0.3807|± |0.0170|
|
| 27 |
+
| | |none | 0|rouge2_diff|-1.5603|± |0.8950|
|
| 28 |
+
| | |none | 0|rougeL_max |44.1785|± |0.8274|
|
| 29 |
+
| | |none | 0|rougeL_acc | 0.4443|± |0.0174|
|
| 30 |
+
| | |none | 0|rougeL_diff|-1.4310|± |0.7806|
|
| 31 |
+
| - truthfulqa_mc1 | 2|none | 0|acc | 0.4174|± |0.0173|
|
| 32 |
+
| - truthfulqa_mc2 | 2|none | 0|acc | 0.5736|± |0.0151|
|
| 33 |
+
|piqa | 1|none | 0|acc | 0.8205|± |0.0090|
|
| 34 |
+
| | |none | 0|acc_norm | 0.8395|± |0.0086|
|
| 35 |
+
|openbookqa | 1|none | 0|acc | 0.3460|± |0.0213|
|
| 36 |
+
| | |none | 0|acc_norm | 0.4800|± |0.0224|
|
| 37 |
+
|mmlu |N/A |none | 0|acc | 0.6300|± |0.0038|
|
| 38 |
+
| - humanities |N/A |none | 0|acc | 0.5779|± |0.0066|
|
| 39 |
+
| - formal_logic | 0|none | 0|acc | 0.4127|± |0.0440|
|
| 40 |
+
| - high_school_european_history | 0|none | 0|acc | 0.8061|± |0.0309|
|
| 41 |
+
| - high_school_us_history | 0|none | 0|acc | 0.8480|± |0.0252|
|
| 42 |
+
| - high_school_world_history | 0|none | 0|acc | 0.8523|± |0.0231|
|
| 43 |
+
| - international_law | 0|none | 0|acc | 0.7934|± |0.0370|
|
| 44 |
+
| - international_law | 0|none | 0|acc | 0.7934|± |0.0370| [46/1966]
|
| 45 |
+
| - jurisprudence | 0|none | 0|acc | 0.7685|± |0.0408|
|
| 46 |
+
| - logical_fallacies | 0|none | 0|acc | 0.7730|± |0.0329|
|
| 47 |
+
| - moral_disputes | 0|none | 0|acc | 0.7110|± |0.0244|
|
| 48 |
+
| - moral_scenarios | 0|none | 0|acc | 0.2894|± |0.0152|
|
| 49 |
+
| - philosophy | 0|none | 0|acc | 0.7106|± |0.0258|
|
| 50 |
+
| - prehistory | 0|none | 0|acc | 0.7685|± |0.0235|
|
| 51 |
+
| - professional_law | 0|none | 0|acc | 0.4824|± |0.0128|
|
| 52 |
+
| - world_religions | 0|none | 0|acc | 0.8129|± |0.0299|
|
| 53 |
+
| - other |N/A |none | 0|acc | 0.7090|± |0.0078|
|
| 54 |
+
| - business_ethics | 0|none | 0|acc | 0.5900|± |0.0494|
|
| 55 |
+
| - clinical_knowledge | 0|none | 0|acc | 0.7245|± |0.0275|
|
| 56 |
+
| - college_medicine | 0|none | 0|acc | 0.6532|± |0.0363|
|
| 57 |
+
| - global_facts | 0|none | 0|acc | 0.3200|± |0.0469|
|
| 58 |
+
| - human_aging | 0|none | 0|acc | 0.7040|± |0.0306|
|
| 59 |
+
| - management | 0|none | 0|acc | 0.7864|± |0.0406|
|
| 60 |
+
| - marketing | 0|none | 0|acc | 0.8632|± |0.0225|
|
| 61 |
+
| - medical_genetics | 0|none | 0|acc | 0.7500|± |0.0435|
|
| 62 |
+
| - miscellaneous | 0|none | 0|acc | 0.8212|± |0.0137|
|
| 63 |
+
| - nutrition | 0|none | 0|acc | 0.7451|± |0.0250|
|
| 64 |
+
| - professional_accounting | 0|none | 0|acc | 0.5000|± |0.0298|
|
| 65 |
+
| - professional_medicine | 0|none | 0|acc | 0.7059|± |0.0277|
|
| 66 |
+
| - virology | 0|none | 0|acc | 0.5301|± |0.0389|
|
| 67 |
+
| - social_sciences |N/A |none | 0|acc | 0.7358|± |0.0077|
|
| 68 |
+
| - econometrics | 0|none | 0|acc | 0.4474|± |0.0468|
|
| 69 |
+
| - high_school_geography | 0|none | 0|acc | 0.7525|± |0.0307|
|
| 70 |
+
| - high_school_government_and_politics| 0|none | 0|acc | 0.9016|± |0.0215|
|
| 71 |
+
| - high_school_macroeconomics | 0|none | 0|acc | 0.6564|± |0.0241|
|
| 72 |
+
| - high_school_microeconomics | 0|none | 0|acc | 0.6807|± |0.0303|
|
| 73 |
+
| - high_school_psychology | 0|none | 0|acc | 0.8404|± |0.0157|
|
| 74 |
+
| - human_sexuality | 0|none | 0|acc | 0.7405|�� |0.0384|
|
| 75 |
+
| - professional_psychology | 0|none | 0|acc | 0.6552|± |0.0192|
|
| 76 |
+
| - public_relations | 0|none | 0|acc | 0.6727|± |0.0449|
|
| 77 |
+
| - security_studies | 0|none | 0|acc | 0.7673|± |0.0270|
|
| 78 |
+
| - sociology | 0|none | 0|acc | 0.8358|± |0.0262|
|
| 79 |
+
| - us_foreign_policy | 0|none | 0|acc | 0.8600|± |0.0349|
|
| 80 |
+
| - stem |N/A |none | 0|acc | 0.5265|± |0.0085|
|
| 81 |
+
| - abstract_algebra | 0|none | 0|acc | 0.3100|± |0.0465|
|
| 82 |
+
| - anatomy | 0|none | 0|acc | 0.6000|± |0.0423|
|
| 83 |
+
| - astronomy | 0|none | 0|acc | 0.6842|± |0.0378|
|
| 84 |
+
| - college_biology | 0|none | 0|acc | 0.7292|± |0.0372|
|
| 85 |
+
| - college_chemistry | 0|none | 0|acc | 0.4700|± |0.0502|
|
| 86 |
+
| - college_chemistry | 0|none | 0|acc | 0.4700|± |0.0502| [5/1966]
|
| 87 |
+
| - college_computer_science | 0|none | 0|acc | 0.5600|± |0.0499|
|
| 88 |
+
| - college_mathematics | 0|none | 0|acc | 0.3500|± |0.0479|
|
| 89 |
+
| - college_physics | 0|none | 0|acc | 0.3529|± |0.0476|
|
| 90 |
+
| - computer_security | 0|none | 0|acc | 0.7100|± |0.0456|
|
| 91 |
+
| - conceptual_physics | 0|none | 0|acc | 0.5574|± |0.0325|
|
| 92 |
+
| - electrical_engineering | 0|none | 0|acc | 0.5793|± |0.0411|
|
| 93 |
+
| - elementary_mathematics | 0|none | 0|acc | 0.4101|± |0.0253|
|
| 94 |
+
| - high_school_biology | 0|none | 0|acc | 0.7903|± |0.0232|
|
| 95 |
+
| - high_school_chemistry | 0|none | 0|acc | 0.4828|± |0.0352|
|
| 96 |
+
| - high_school_computer_science | 0|none | 0|acc | 0.6600|± |0.0476|
|
| 97 |
+
| - high_school_mathematics | 0|none | 0|acc | 0.3444|± |0.0290|
|
| 98 |
+
| - high_school_physics | 0|none | 0|acc | 0.3642|± |0.0393|
|
| 99 |
+
| - high_school_statistics | 0|none | 0|acc | 0.5000|± |0.0341|
|
| 100 |
+
| - machine_learning | 0|none | 0|acc | 0.5268|± |0.0474|
|
| 101 |
+
|hellaswag | 1|none | 0|acc | 0.6537|± |0.0047|
|
| 102 |
+
| | |none | 0|acc_norm | 0.8429|± |0.0036|
|
| 103 |
+
|gsm8k | 3|strict-match | 5|exact_match| 0.7218|± |0.0123|
|
| 104 |
+
| | |flexible-extract| 5|exact_match| 0.7263|± |0.0123|
|
| 105 |
+
|boolq | 2|none | 0|acc | 0.8743|± |0.0058|
|
| 106 |
+
|arc_easy | 1|none | 0|acc | 0.8502|± |0.0073|
|
| 107 |
+
| | |none | 0|acc_norm | 0.8295|± |0.0077|
|
| 108 |
+
|arc_challenge | 1|none | 0|acc | 0.5964|± |0.0143|
|
| 109 |
+
| | |none | 0|acc_norm | 0.6169|± |0.0142|
|
| 110 |
+
|
| 111 |
+
| Groups |Version|Filter|n-shot| Metric | Value | |Stderr|
|
| 112 |
+
|------------------|-------|------|-----:|-----------|------:|---|-----:|
|
| 113 |
+
|truthfulqa |N/A |none | 0|rouge1_max |47.8575|± |0.8139|
|
| 114 |
+
| | |none | 0|bleu_max |21.9412|± |0.7280|
|
| 115 |
+
| | |none | 0|rouge2_max |32.7726|± |0.9228|
|
| 116 |
+
| | |none | 0|rougeL_diff|-1.4310|± |0.7806|
|
| 117 |
+
| | |none | 0|acc | 0.4955|± |0.0115|
|
| 118 |
+
| | |none | 0|bleu_diff |-0.2883|± |0.6228|
|
| 119 |
+
| | |none | 0|rouge2_acc | 0.3807|± |0.0170|
|
| 120 |
+
| | |none | 0|rougeL_max |44.1785|± |0.8274|
|
| 121 |
+
| | |none | 0|rougeL_acc | 0.4443|± |0.0174|
|
| 122 |
+
| | |none | 0|rouge2_diff|-1.5603|± |0.8950|
|
| 123 |
+
| | |none | 0|bleu_acc | 0.4321|± |0.0173|
|
| 124 |
+
| | |none | 0|rouge1_diff|-0.7276|± |0.7721|
|
| 125 |
+
| | |none | 0|rouge1_acc | 0.4774|± |0.0175|
|
| 126 |
+
|mmlu |N/A |none | 0|acc | 0.6300|± |0.0038|
|
| 127 |
+
| - humanities |N/A |none | 0|acc | 0.5779|± |0.0066|
|
| 128 |
+
| - other |N/A |none | 0|acc | 0.7090|± |0.0078|
|
| 129 |
+
| - social_sciences|N/A |none | 0|acc | 0.7358|± |0.0077|
|
| 130 |
+
| - stem |N/A |none | 0|acc | 0.5265|± |0.0085|
|
bench-mistral.txt
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
mistralai/Mistral-7B-Instruct-v0.2
|
| 2 |
+
|
| 3 |
+
| Tasks |Version| Filter |n-shot| Metric | Value | |Stderr|
|
| 4 |
+
|---------------------------------------|-------|----------------|-----:|-----------|------:|---|-----:|
|
| 5 |
+
|winogrande | 1|none | 0|acc | 0.7364|± |0.0124|
|
| 6 |
+
|truthfulqa |N/A |none | 0|acc | 0.5954|± |0.0116|
|
| 7 |
+
| | |none | 0|rouge1_max |46.4534|± |0.8502|
|
| 8 |
+
| | |none | 0|rougeL_diff| 5.5378|± |0.8859|
|
| 9 |
+
| | |none | 0|bleu_acc | 0.5483|± |0.0174|
|
| 10 |
+
| | |none | 0|rouge2_max |31.1969|± |0.9785|
|
| 11 |
+
| | |none | 0|rougeL_max |43.4263|± |0.8666|
|
| 12 |
+
| | |none | 0|rougeL_acc | 0.5606|± |0.0174|
|
| 13 |
+
| | |none | 0|rouge2_acc | 0.4529|± |0.0174|
|
| 14 |
+
| | |none | 0|rouge2_diff| 5.3591|± |0.9416|
|
| 15 |
+
| | |none | 0|bleu_max |21.2977|± |0.7504|
|
| 16 |
+
| | |none | 0|rouge1_acc | 0.5741|± |0.0173|
|
| 17 |
+
| | |none | 0|bleu_diff | 4.3215|± |0.6161|
|
| 18 |
+
| | |none | 0|rouge1_diff| 5.7381|± |0.8786|
|
| 19 |
+
| - truthfulqa_gen | 3|none | 0|bleu_max |21.2977|± |0.7504|
|
| 20 |
+
| | |none | 0|bleu_acc | 0.5483|± |0.0174|
|
| 21 |
+
| | |none | 0|bleu_diff | 4.3215|± |0.6161|
|
| 22 |
+
| | |none | 0|rouge1_max |46.4534|± |0.8502|
|
| 23 |
+
| | |none | 0|rouge1_acc | 0.5741|± |0.0173|
|
| 24 |
+
| | |none | 0|rouge1_diff| 5.7381|± |0.8786|
|
| 25 |
+
| | |none | 0|rouge2_max |31.1969|± |0.9785|
|
| 26 |
+
| | |none | 0|rouge2_acc | 0.4529|± |0.0174|
|
| 27 |
+
| | |none | 0|rouge2_diff| 5.3591|± |0.9416|
|
| 28 |
+
| | |none | 0|rougeL_max |43.4263|± |0.8666|
|
| 29 |
+
| | |none | 0|rougeL_acc | 0.5606|± |0.0174|
|
| 30 |
+
| | |none | 0|rougeL_diff| 5.5378|± |0.8859|
|
| 31 |
+
| - truthfulqa_mc1 | 2|none | 0|acc | 0.5226|± |0.0175|
|
| 32 |
+
| - truthfulqa_mc2 | 2|none | 0|acc | 0.6681|± |0.0153|
|
| 33 |
+
|piqa | 1|none | 0|acc | 0.8003|± |0.0093|
|
| 34 |
+
| | |none | 0|acc_norm | 0.8047|± |0.0092|
|
| 35 |
+
|openbookqa | 1|none | 0|acc | 0.3600|± |0.0215|
|
| 36 |
+
| | |none | 0|acc_norm | 0.4520|± |0.0223|
|
| 37 |
+
|mmlu |N/A |none | 0|acc | 0.5879|± |0.0039|
|
| 38 |
+
| - humanities |N/A |none | 0|acc | 0.5396|± |0.0069|
|
| 39 |
+
| - formal_logic | 0|none | 0|acc | 0.3651|± |0.0431|
|
| 40 |
+
| - high_school_european_history | 0|none | 0|acc | 0.7273|± |0.0348|
|
| 41 |
+
| - high_school_us_history | 0|none | 0|acc | 0.7794|± |0.0291|
|
| 42 |
+
| - high_school_world_history | 0|none | 0|acc | 0.7764|± |0.0271|
|
| 43 |
+
| - international_law | 0|none | 0|acc | 0.7438|± |0.0398|
|
| 44 |
+
| - jurisprudence | 0|none | 0|acc | 0.7130|± |0.0437|
|
| 45 |
+
| - logical_fallacies | 0|none | 0|acc | 0.7546|± |0.0338|
|
| 46 |
+
| - moral_disputes | 0|none | 0|acc | 0.6532|± |0.0256|
|
| 47 |
+
| - moral_scenarios | 0|none | 0|acc | 0.3564|± |0.0160|
|
| 48 |
+
| - philosophy | 0|none | 0|acc | 0.6463|± |0.0272|
|
| 49 |
+
| - prehistory | 0|none | 0|acc | 0.6821|± |0.0259|
|
| 50 |
+
| - professional_law | 0|none | 0|acc | 0.4133|± |0.0126|
|
| 51 |
+
| - world_religions | 0|none | 0|acc | 0.8129|± |0.0299|
|
| 52 |
+
| - other |N/A |none | 0|acc | 0.6621|± |0.0082|
|
| 53 |
+
| - business_ethics | 0|none | 0|acc | 0.5900|± |0.0494|
|
| 54 |
+
| - clinical_knowledge | 0|none | 0|acc | 0.6491|± |0.0294|
|
| 55 |
+
| - college_medicine | 0|none | 0|acc | 0.5549|± |0.0379|
|
| 56 |
+
| - global_facts | 0|none | 0|acc | 0.3800|± |0.0488|
|
| 57 |
+
| - human_aging | 0|none | 0|acc | 0.6233|± |0.0325|
|
| 58 |
+
| - management | 0|none | 0|acc | 0.7184|± |0.0445|
|
| 59 |
+
| - marketing | 0|none | 0|acc | 0.8761|± |0.0216|
|
| 60 |
+
| - medical_genetics | 0|none | 0|acc | 0.6500|± |0.0479|
|
| 61 |
+
| - miscellaneous | 0|none | 0|acc | 0.7944|± |0.0145|
|
| 62 |
+
| - nutrition | 0|none | 0|acc | 0.6732|± |0.0269|
|
| 63 |
+
| - professional_accounting | 0|none | 0|acc | 0.4468|± |0.0297|
|
| 64 |
+
| - professional_medicine | 0|none | 0|acc | 0.6581|± |0.0288|
|
| 65 |
+
| - virology | 0|none | 0|acc | 0.4578|± |0.0388|
|
| 66 |
+
| - social_sciences |N/A |none | 0|acc | 0.6799|± |0.0082|
|
| 67 |
+
| - econometrics | 0|none | 0|acc | 0.4649|± |0.0469|
|
| 68 |
+
| - high_school_geography | 0|none | 0|acc | 0.7374|± |0.0314|
|
| 69 |
+
| - high_school_government_and_politics| 0|none | 0|acc | 0.8031|± |0.0287|
|
| 70 |
+
| - high_school_macroeconomics | 0|none | 0|acc | 0.5590|± |0.0252|
|
| 71 |
+
| - high_school_microeconomics | 0|none | 0|acc | 0.6387|± |0.0312|
|
| 72 |
+
| - high_school_psychology | 0|none | 0|acc | 0.7853|± |0.0176|
|
| 73 |
+
| - human_sexuality | 0|none | 0|acc | 0.6794|± |0.0409|
|
| 74 |
+
| - professional_psychology | 0|none | 0|acc | 0.5866|± |0.0199|
|
| 75 |
+
| - public_relations | 0|none | 0|acc | 0.6455|± |0.0458|
|
| 76 |
+
| - security_studies | 0|none | 0|acc | 0.6816|± |0.0298|
|
| 77 |
+
| - sociology | 0|none | 0|acc | 0.8408|± |0.0259|
|
| 78 |
+
| - us_foreign_policy | 0|none | 0|acc | 0.8500|± |0.0359|
|
| 79 |
+
| - stem |N/A |none | 0|acc | 0.4970|± |0.0087|
|
| 80 |
+
| - abstract_algebra | 0|none | 0|acc | 0.3200|± |0.0469|
|
| 81 |
+
| - anatomy | 0|none | 0|acc | 0.5704|± |0.0428|
|
| 82 |
+
| - astronomy | 0|none | 0|acc | 0.6382|± |0.0391|
|
| 83 |
+
| - college_biology | 0|none | 0|acc | 0.6597|± |0.0396|
|
| 84 |
+
| - college_chemistry | 0|none | 0|acc | 0.4100|± |0.0494|
|
| 85 |
+
| - college_computer_science | 0|none | 0|acc | 0.5400|± |0.0501|
|
| 86 |
+
| - college_mathematics | 0|none | 0|acc | 0.3400|± |0.0476|
|
| 87 |
+
| - college_physics | 0|none | 0|acc | 0.3725|± |0.0481|
|
| 88 |
+
| - computer_security | 0|none | 0|acc | 0.6700|± |0.0473|
|
| 89 |
+
| - conceptual_physics | 0|none | 0|acc | 0.4809|± |0.0327|
|
| 90 |
+
| - electrical_engineering | 0|none | 0|acc | 0.5931|± |0.0409|
|
| 91 |
+
| - elementary_mathematics | 0|none | 0|acc | 0.4233|± |0.0254|
|
| 92 |
+
| - high_school_biology | 0|none | 0|acc | 0.6774|± |0.0266|
|
| 93 |
+
| - high_school_chemistry | 0|none | 0|acc | 0.4877|± |0.0352|
|
| 94 |
+
| - high_school_computer_science | 0|none | 0|acc | 0.6100|± |0.0490|
|
| 95 |
+
| - high_school_mathematics | 0|none | 0|acc | 0.3556|± |0.0292|
|
| 96 |
+
| - high_school_physics | 0|none | 0|acc | 0.3642|± |0.0393|
|
| 97 |
+
| - high_school_statistics | 0|none | 0|acc | 0.4630|± |0.0340|
|
| 98 |
+
| - machine_learning | 0|none | 0|acc | 0.4643|± |0.0473|
|
| 99 |
+
|hellaswag | 1|none | 0|acc | 0.6608|± |0.0047|
|
| 100 |
+
| | |none | 0|acc_norm | 0.8368|± |0.0037|
|
| 101 |
+
|gsm8k | 3|strict-match | 5|exact_match| 0.4155|± |0.0136|
|
| 102 |
+
| | |flexible-extract| 5|exact_match| 0.4193|± |0.0136|
|
| 103 |
+
|boolq | 2|none | 0|acc | 0.8529|± |0.0062|
|
| 104 |
+
|arc_easy | 1|none | 0|acc | 0.8136|± |0.0080|
|
| 105 |
+
| | |none | 0|acc_norm | 0.7660|± |0.0087|
|
| 106 |
+
|arc_challenge | 1|none | 0|acc | 0.5435|± |0.0146|
|
| 107 |
+
| | |none | 0|acc_norm | 0.5580|± |0.0145|
|
| 108 |
+
|
| 109 |
+
| Groups |Version|Filter|n-shot| Metric | Value | |Stderr|
|
| 110 |
+
|------------------|-------|------|-----:|-----------|------:|---|-----:|
|
| 111 |
+
|truthfulqa |N/A |none | 0|acc | 0.5954|± |0.0116|
|
| 112 |
+
| | |none | 0|rouge1_max |46.4534|± |0.8502|
|
| 113 |
+
| | |none | 0|rougeL_diff| 5.5378|± |0.8859|
|
| 114 |
+
| | |none | 0|bleu_acc | 0.5483|± |0.0174|
|
| 115 |
+
| | |none | 0|rouge2_max |31.1969|± |0.9785|
|
| 116 |
+
| | |none | 0|rougeL_max |43.4263|± |0.8666|
|
| 117 |
+
| | |none | 0|rougeL_acc | 0.5606|± |0.0174|
|
| 118 |
+
| | |none | 0|rouge2_acc | 0.4529|± |0.0174|
|
| 119 |
+
| | |none | 0|rouge2_diff| 5.3591|± |0.9416|
|
| 120 |
+
| | |none | 0|bleu_max |21.2977|± |0.7504|
|
| 121 |
+
| | |none | 0|rouge1_acc | 0.5741|± |0.0173|
|
| 122 |
+
| | |none | 0|bleu_diff | 4.3215|± |0.6161|
|
| 123 |
+
| | |none | 0|rouge1_diff| 5.7381|± |0.8786|
|
| 124 |
+
|mmlu |N/A |none | 0|acc | 0.5879|± |0.0039|
|
| 125 |
+
| - humanities |N/A |none | 0|acc | 0.5396|± |0.0069|
|
| 126 |
+
| - other |N/A |none | 0|acc | 0.6621|± |0.0082|
|
| 127 |
+
| - social_sciences|N/A |none | 0|acc | 0.6799|± |0.0082|
|
| 128 |
+
| - stem |N/A |none | 0|acc | 0.4970|± |0.0087|
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "raidhon/coven_7b_128k_orpo_alpha",
|
| 3 |
+
"architectures": ["MistralForCausalLM"],
|
| 4 |
+
"attention_dropout": 0.0,
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"hidden_act": "silu",
|
| 8 |
+
"hidden_size": 4096,
|
| 9 |
+
"initializer_range": 0.02,
|
| 10 |
+
"intermediate_size": 14336,
|
| 11 |
+
"max_position_embeddings": 32768,
|
| 12 |
+
"max_sequence_length": 131072,
|
| 13 |
+
"model_type": "mistral",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"num_key_value_heads": 8,
|
| 17 |
+
"rms_norm_eps": 1e-5,
|
| 18 |
+
"rope_scaling": {
|
| 19 |
+
"factor": 4.0,
|
| 20 |
+
"finetuned": true,
|
| 21 |
+
"original_max_position_embeddings": 32768,
|
| 22 |
+
"type": "yarn"
|
| 23 |
+
},
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"sliding_window": 131072,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.39.3",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 32000
|
| 31 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae114d2ad6ffb2f589ba9085c22a114f63650b5e18b4bbc18355589df8006b48
|
| 3 |
+
size 9919903616
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9aca265234f2460495e81ead1f264d5ee78b8fb0dc3c10aeba69dc2e11bd089
|
| 3 |
+
size 4563594120
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"lm_head.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"additional_special_tokens": [
|
| 32 |
+
"<unk>",
|
| 33 |
+
"<s>",
|
| 34 |
+
"</s>"
|
| 35 |
+
],
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}",
|
| 38 |
+
"clean_up_tokenization_spaces": false,
|
| 39 |
+
"eos_token": "</s>",
|
| 40 |
+
"legacy": true,
|
| 41 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 42 |
+
"pad_token": "</s>",
|
| 43 |
+
"padding_side": "left",
|
| 44 |
+
"sp_model_kwargs": {},
|
| 45 |
+
"spaces_between_special_tokens": false,
|
| 46 |
+
"split_special_tokens": false,
|
| 47 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"use_default_system_prompt": true
|
| 50 |
+
}
|