llmenthusiast
commited on
Commit
•
ce665aa
1
Parent(s):
ee06628
upload 13b
Browse files- README.md +201 -94
- adapter_config.json +5 -5
- adapter_model.bin +2 -2
- config.json +0 -39
- merged/config.json +6 -6
- merged/{pytorch_model-00001-of-00002.bin → pytorch_model-00001-of-00003.bin} +2 -2
- merged/{pytorch_model-00002-of-00002.bin → pytorch_model-00002-of-00003.bin} +2 -2
- merged/pytorch_model-00003-of-00003.bin +3 -0
- merged/pytorch_model.bin.index.json +364 -292
- special_tokens_map.json +0 -24
- tokenizer_config.json +0 -45
- tokenizer.model → training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,112 +1,219 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
- generated_from_trainer
|
| 5 |
-
model-index:
|
| 6 |
-
- name: llama-le-out
|
| 7 |
-
results: []
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
| 11 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
-
|
| 14 |
-
# llama-le-out
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.6239
|
| 19 |
|
| 20 |
-
## Model description
|
| 21 |
|
| 22 |
-
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
-
## Training and evaluation data
|
| 29 |
|
| 30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
|
| 32 |
## Training procedure
|
| 33 |
|
| 34 |
-
### Training hyperparameters
|
| 35 |
-
|
| 36 |
-
The following hyperparameters were used during training:
|
| 37 |
-
- learning_rate: 0.0002
|
| 38 |
-
- train_batch_size: 4
|
| 39 |
-
- eval_batch_size: 4
|
| 40 |
-
- seed: 42
|
| 41 |
-
- distributed_type: multi-GPU
|
| 42 |
-
- num_devices: 4
|
| 43 |
-
- gradient_accumulation_steps: 2
|
| 44 |
-
- total_train_batch_size: 32
|
| 45 |
-
- total_eval_batch_size: 16
|
| 46 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
-
- lr_scheduler_type: cosine
|
| 48 |
-
- lr_scheduler_warmup_steps: 10
|
| 49 |
-
- num_epochs: 3
|
| 50 |
-
|
| 51 |
-
### Training results
|
| 52 |
-
|
| 53 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 0.9364 | 0.06 | 100 | 0.8000 |
|
| 56 |
-
| 0.809 | 0.12 | 200 | 0.7724 |
|
| 57 |
-
| 0.8695 | 0.18 | 300 | 0.7571 |
|
| 58 |
-
| 0.7512 | 0.24 | 400 | 0.7406 |
|
| 59 |
-
| 0.8266 | 0.3 | 500 | 0.7327 |
|
| 60 |
-
| 0.7898 | 0.35 | 600 | 0.7238 |
|
| 61 |
-
| 0.9163 | 0.41 | 700 | 0.7135 |
|
| 62 |
-
| 0.6955 | 0.47 | 800 | 0.7025 |
|
| 63 |
-
| 0.7887 | 0.53 | 900 | 0.7009 |
|
| 64 |
-
| 0.7361 | 0.59 | 1000 | 0.6911 |
|
| 65 |
-
| 0.7736 | 0.65 | 1100 | 0.6897 |
|
| 66 |
-
| 0.7135 | 0.71 | 1200 | 0.6859 |
|
| 67 |
-
| 0.8138 | 0.77 | 1300 | 0.6788 |
|
| 68 |
-
| 0.7172 | 0.83 | 1400 | 0.6720 |
|
| 69 |
-
| 0.7387 | 0.89 | 1500 | 0.6695 |
|
| 70 |
-
| 0.7042 | 0.95 | 1600 | 0.6688 |
|
| 71 |
-
| 0.7231 | 1.0 | 1700 | 0.6652 |
|
| 72 |
-
| 0.7136 | 1.06 | 1800 | 0.6626 |
|
| 73 |
-
| 0.694 | 1.12 | 1900 | 0.6583 |
|
| 74 |
-
| 0.7401 | 1.18 | 2000 | 0.6551 |
|
| 75 |
-
| 0.63 | 1.24 | 2100 | 0.6519 |
|
| 76 |
-
| 0.6506 | 1.3 | 2200 | 0.6478 |
|
| 77 |
-
| 0.7436 | 1.36 | 2300 | 0.6457 |
|
| 78 |
-
| 0.5903 | 1.42 | 2400 | 0.6452 |
|
| 79 |
-
| 0.6861 | 1.48 | 2500 | 0.6399 |
|
| 80 |
-
| 0.6576 | 1.54 | 2600 | 0.6412 |
|
| 81 |
-
| 0.6327 | 1.59 | 2700 | 0.6357 |
|
| 82 |
-
| 0.6634 | 1.65 | 2800 | 0.6378 |
|
| 83 |
-
| 0.6419 | 1.71 | 2900 | 0.6349 |
|
| 84 |
-
| 0.6573 | 1.77 | 3000 | 0.6344 |
|
| 85 |
-
| 0.7052 | 1.83 | 3100 | 0.6327 |
|
| 86 |
-
| 0.6438 | 1.89 | 3200 | 0.6292 |
|
| 87 |
-
| 0.713 | 1.95 | 3300 | 0.6283 |
|
| 88 |
-
| 0.6357 | 2.01 | 3400 | 0.6293 |
|
| 89 |
-
| 0.5736 | 2.07 | 3500 | 0.6302 |
|
| 90 |
-
| 0.591 | 2.13 | 3600 | 0.6307 |
|
| 91 |
-
| 0.6995 | 2.19 | 3700 | 0.6295 |
|
| 92 |
-
| 0.6708 | 2.24 | 3800 | 0.6277 |
|
| 93 |
-
| 0.6329 | 2.3 | 3900 | 0.6262 |
|
| 94 |
-
| 0.6138 | 2.36 | 4000 | 0.6271 |
|
| 95 |
-
| 0.6316 | 2.42 | 4100 | 0.6266 |
|
| 96 |
-
| 0.6022 | 2.48 | 4200 | 0.6260 |
|
| 97 |
-
| 0.7221 | 2.54 | 4300 | 0.6252 |
|
| 98 |
-
| 0.6943 | 2.6 | 4400 | 0.6256 |
|
| 99 |
-
| 0.6616 | 2.66 | 4500 | 0.6246 |
|
| 100 |
-
| 0.6185 | 2.72 | 4600 | 0.6247 |
|
| 101 |
-
| 0.6417 | 2.78 | 4700 | 0.6239 |
|
| 102 |
-
| 0.6238 | 2.84 | 4800 | 0.6237 |
|
| 103 |
-
| 0.6024 | 2.89 | 4900 | 0.6236 |
|
| 104 |
-
| 0.6059 | 2.95 | 5000 | 0.6239 |
|
| 105 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
|
| 107 |
### Framework versions
|
| 108 |
|
| 109 |
-
|
| 110 |
-
-
|
| 111 |
-
- Datasets 2.14.6
|
| 112 |
-
- Tokenizers 0.14.1
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: meta-llama/Llama-2-13b-chat-hf
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
+
# Model Card for Model ID
|
|
|
|
| 7 |
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
|
|
|
| 9 |
|
|
|
|
|
|
|
|
|
|
| 10 |
|
|
|
|
| 11 |
|
| 12 |
+
## Model Details
|
| 13 |
|
| 14 |
+
### Model Description
|
| 15 |
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
|
|
|
|
| 18 |
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 22 |
+
- **Model type:** [More Information Needed]
|
| 23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 24 |
+
- **License:** [More Information Needed]
|
| 25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 26 |
+
|
| 27 |
+
### Model Sources [optional]
|
| 28 |
+
|
| 29 |
+
<!-- Provide the basic links for the model. -->
|
| 30 |
+
|
| 31 |
+
- **Repository:** [More Information Needed]
|
| 32 |
+
- **Paper [optional]:** [More Information Needed]
|
| 33 |
+
- **Demo [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
## Uses
|
| 36 |
+
|
| 37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 38 |
+
|
| 39 |
+
### Direct Use
|
| 40 |
+
|
| 41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 42 |
+
|
| 43 |
+
[More Information Needed]
|
| 44 |
+
|
| 45 |
+
### Downstream Use [optional]
|
| 46 |
+
|
| 47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 48 |
+
|
| 49 |
+
[More Information Needed]
|
| 50 |
+
|
| 51 |
+
### Out-of-Scope Use
|
| 52 |
+
|
| 53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 54 |
+
|
| 55 |
+
[More Information Needed]
|
| 56 |
+
|
| 57 |
+
## Bias, Risks, and Limitations
|
| 58 |
+
|
| 59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 60 |
+
|
| 61 |
+
[More Information Needed]
|
| 62 |
+
|
| 63 |
+
### Recommendations
|
| 64 |
+
|
| 65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 66 |
+
|
| 67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 68 |
+
|
| 69 |
+
## How to Get Started with the Model
|
| 70 |
+
|
| 71 |
+
Use the code below to get started with the model.
|
| 72 |
+
|
| 73 |
+
[More Information Needed]
|
| 74 |
+
|
| 75 |
+
## Training Details
|
| 76 |
+
|
| 77 |
+
### Training Data
|
| 78 |
+
|
| 79 |
+
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
### Training Procedure
|
| 84 |
+
|
| 85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 86 |
+
|
| 87 |
+
#### Preprocessing [optional]
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
#### Training Hyperparameters
|
| 93 |
+
|
| 94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 95 |
+
|
| 96 |
+
#### Speeds, Sizes, Times [optional]
|
| 97 |
+
|
| 98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 99 |
+
|
| 100 |
+
[More Information Needed]
|
| 101 |
+
|
| 102 |
+
## Evaluation
|
| 103 |
+
|
| 104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 105 |
+
|
| 106 |
+
### Testing Data, Factors & Metrics
|
| 107 |
+
|
| 108 |
+
#### Testing Data
|
| 109 |
+
|
| 110 |
+
<!-- This should link to a Data Card if possible. -->
|
| 111 |
+
|
| 112 |
+
[More Information Needed]
|
| 113 |
+
|
| 114 |
+
#### Factors
|
| 115 |
+
|
| 116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 117 |
+
|
| 118 |
+
[More Information Needed]
|
| 119 |
+
|
| 120 |
+
#### Metrics
|
| 121 |
+
|
| 122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 123 |
+
|
| 124 |
+
[More Information Needed]
|
| 125 |
+
|
| 126 |
+
### Results
|
| 127 |
+
|
| 128 |
+
[More Information Needed]
|
| 129 |
+
|
| 130 |
+
#### Summary
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
## Model Examination [optional]
|
| 135 |
+
|
| 136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 137 |
+
|
| 138 |
+
[More Information Needed]
|
| 139 |
+
|
| 140 |
+
## Environmental Impact
|
| 141 |
+
|
| 142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 143 |
+
|
| 144 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 145 |
+
|
| 146 |
+
- **Hardware Type:** [More Information Needed]
|
| 147 |
+
- **Hours used:** [More Information Needed]
|
| 148 |
+
- **Cloud Provider:** [More Information Needed]
|
| 149 |
+
- **Compute Region:** [More Information Needed]
|
| 150 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 151 |
+
|
| 152 |
+
## Technical Specifications [optional]
|
| 153 |
+
|
| 154 |
+
### Model Architecture and Objective
|
| 155 |
+
|
| 156 |
+
[More Information Needed]
|
| 157 |
+
|
| 158 |
+
### Compute Infrastructure
|
| 159 |
+
|
| 160 |
+
[More Information Needed]
|
| 161 |
+
|
| 162 |
+
#### Hardware
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
#### Software
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
## Citation [optional]
|
| 171 |
+
|
| 172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 173 |
+
|
| 174 |
+
**BibTeX:**
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
**APA:**
|
| 179 |
+
|
| 180 |
+
[More Information Needed]
|
| 181 |
+
|
| 182 |
+
## Glossary [optional]
|
| 183 |
+
|
| 184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 185 |
+
|
| 186 |
+
[More Information Needed]
|
| 187 |
+
|
| 188 |
+
## More Information [optional]
|
| 189 |
+
|
| 190 |
+
[More Information Needed]
|
| 191 |
+
|
| 192 |
+
## Model Card Authors [optional]
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## Model Card Contact
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
|
| 201 |
## Training procedure
|
| 202 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
|
| 204 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 205 |
+
- quant_method: bitsandbytes
|
| 206 |
+
- load_in_8bit: False
|
| 207 |
+
- load_in_4bit: True
|
| 208 |
+
- llm_int8_threshold: 6.0
|
| 209 |
+
- llm_int8_skip_modules: None
|
| 210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 211 |
+
- llm_int8_has_fp16_weight: False
|
| 212 |
+
- bnb_4bit_quant_type: nf4
|
| 213 |
+
- bnb_4bit_use_double_quant: True
|
| 214 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 215 |
|
| 216 |
### Framework versions
|
| 217 |
|
| 218 |
+
|
| 219 |
+
- PEFT 0.6.0.dev0
|
|
|
|
|
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "meta-llama/Llama-2-
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": null,
|
| 7 |
"inference_mode": true,
|
|
@@ -16,13 +16,13 @@
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
| 19 |
-
"o_proj",
|
| 20 |
-
"gate_proj",
|
| 21 |
"up_proj",
|
|
|
|
|
|
|
| 22 |
"v_proj",
|
|
|
|
| 23 |
"down_proj",
|
| 24 |
-
"
|
| 25 |
-
"q_proj"
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
|
| 5 |
"bias": "none",
|
| 6 |
"fan_in_fan_out": null,
|
| 7 |
"inference_mode": true,
|
|
|
|
| 16 |
"rank_pattern": {},
|
| 17 |
"revision": null,
|
| 18 |
"target_modules": [
|
|
|
|
|
|
|
| 19 |
"up_proj",
|
| 20 |
+
"k_proj",
|
| 21 |
+
"q_proj",
|
| 22 |
"v_proj",
|
| 23 |
+
"gate_proj",
|
| 24 |
"down_proj",
|
| 25 |
+
"o_proj"
|
|
|
|
| 26 |
],
|
| 27 |
"task_type": "CAUSAL_LM"
|
| 28 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ed836838f97e53c03e5a23bb0da1386ab66d228865a526b7186968cca02f128
|
| 3 |
+
size 500897101
|
config.json
DELETED
|
@@ -1,39 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LlamaForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"bos_token_id": 1,
|
| 8 |
-
"eos_token_id": 2,
|
| 9 |
-
"hidden_act": "silu",
|
| 10 |
-
"hidden_size": 4096,
|
| 11 |
-
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size": 11008,
|
| 13 |
-
"max_position_embeddings": 4096,
|
| 14 |
-
"model_type": "llama",
|
| 15 |
-
"num_attention_heads": 32,
|
| 16 |
-
"num_hidden_layers": 32,
|
| 17 |
-
"num_key_value_heads": 32,
|
| 18 |
-
"pretraining_tp": 1,
|
| 19 |
-
"quantization_config": {
|
| 20 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
| 21 |
-
"bnb_4bit_quant_type": "nf4",
|
| 22 |
-
"bnb_4bit_use_double_quant": true,
|
| 23 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 24 |
-
"llm_int8_has_fp16_weight": false,
|
| 25 |
-
"llm_int8_skip_modules": null,
|
| 26 |
-
"llm_int8_threshold": 6.0,
|
| 27 |
-
"load_in_4bit": true,
|
| 28 |
-
"load_in_8bit": false,
|
| 29 |
-
"quant_method": "bitsandbytes"
|
| 30 |
-
},
|
| 31 |
-
"rms_norm_eps": 1e-05,
|
| 32 |
-
"rope_scaling": null,
|
| 33 |
-
"rope_theta": 10000.0,
|
| 34 |
-
"tie_word_embeddings": false,
|
| 35 |
-
"torch_dtype": "float16",
|
| 36 |
-
"transformers_version": "4.34.1",
|
| 37 |
-
"use_cache": false,
|
| 38 |
-
"vocab_size": 32000
|
| 39 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
merged/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "meta-llama/Llama-2-
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
@@ -7,14 +7,14 @@
|
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
-
"hidden_size":
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size":
|
| 13 |
"max_position_embeddings": 4096,
|
| 14 |
"model_type": "llama",
|
| 15 |
-
"num_attention_heads":
|
| 16 |
-
"num_hidden_layers":
|
| 17 |
-
"num_key_value_heads":
|
| 18 |
"pretraining_tp": 1,
|
| 19 |
"rms_norm_eps": 1e-05,
|
| 20 |
"rope_scaling": null,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
|
| 3 |
"architectures": [
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
|
|
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 5120,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 13824,
|
| 13 |
"max_position_embeddings": 4096,
|
| 14 |
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 40,
|
| 16 |
+
"num_hidden_layers": 40,
|
| 17 |
+
"num_key_value_heads": 40,
|
| 18 |
"pretraining_tp": 1,
|
| 19 |
"rms_norm_eps": 1e-05,
|
| 20 |
"rope_scaling": null,
|
merged/{pytorch_model-00001-of-00002.bin → pytorch_model-00001-of-00003.bin}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61f9e03951f28f812b2070353bf20fb1268723a60691a7d6f41394450ce6a678
|
| 3 |
+
size 9948721353
|
merged/{pytorch_model-00002-of-00002.bin → pytorch_model-00002-of-00003.bin}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8cf7d7923b34367fa54b0698c95a3a2d8f77a87d69d96efb77ecaa3baeca941
|
| 3 |
+
size 9904157328
|
merged/pytorch_model-00003-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b9066b0bc392571f8f558b196e68823463621c1a170ce6b1528d5ba482b5aec
|
| 3 |
+
size 6178979423
|
merged/pytorch_model.bin.index.json
CHANGED
|
@@ -1,298 +1,370 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "pytorch_model-
|
| 7 |
-
"model.embed_tokens.weight": "pytorch_model-00001-of-
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 13 |
-
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 14 |
-
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 15 |
-
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 16 |
-
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 17 |
-
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-
|
| 18 |
-
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 19 |
-
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 20 |
-
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 21 |
-
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 22 |
-
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 23 |
-
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 24 |
-
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 25 |
-
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 26 |
-
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-
|
| 27 |
-
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 28 |
-
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 29 |
-
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 30 |
-
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 31 |
-
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 32 |
-
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 33 |
-
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 34 |
-
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 35 |
-
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-
|
| 36 |
-
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 37 |
-
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 38 |
-
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 39 |
-
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 40 |
-
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 41 |
-
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 42 |
-
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 43 |
-
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 44 |
-
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-
|
| 45 |
-
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 46 |
-
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 47 |
-
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 48 |
-
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 49 |
-
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 50 |
-
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 51 |
-
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 52 |
-
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 53 |
-
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-
|
| 54 |
-
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 55 |
-
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 56 |
-
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 57 |
-
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 58 |
-
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 59 |
-
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 60 |
-
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 61 |
-
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 62 |
-
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-
|
| 63 |
-
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 64 |
-
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 65 |
-
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 66 |
-
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 67 |
-
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 68 |
-
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 69 |
-
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 70 |
-
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 71 |
-
"model.layers.15.input_layernorm.weight": "pytorch_model-
|
| 72 |
-
"model.layers.15.mlp.down_proj.weight": "pytorch_model-
|
| 73 |
-
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-
|
| 74 |
-
"model.layers.15.mlp.up_proj.weight": "pytorch_model-
|
| 75 |
-
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-
|
| 76 |
-
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 77 |
-
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-
|
| 78 |
-
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 79 |
-
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-
|
| 80 |
-
"model.layers.16.input_layernorm.weight": "pytorch_model-
|
| 81 |
-
"model.layers.16.mlp.down_proj.weight": "pytorch_model-
|
| 82 |
-
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-
|
| 83 |
-
"model.layers.16.mlp.up_proj.weight": "pytorch_model-
|
| 84 |
-
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-
|
| 85 |
-
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-
|
| 86 |
-
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-
|
| 87 |
-
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-
|
| 88 |
-
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-
|
| 89 |
-
"model.layers.17.input_layernorm.weight": "pytorch_model-
|
| 90 |
-
"model.layers.17.mlp.down_proj.weight": "pytorch_model-
|
| 91 |
-
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-
|
| 92 |
-
"model.layers.17.mlp.up_proj.weight": "pytorch_model-
|
| 93 |
-
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-
|
| 94 |
-
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-
|
| 95 |
-
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-
|
| 96 |
-
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-
|
| 97 |
-
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-
|
| 98 |
-
"model.layers.18.input_layernorm.weight": "pytorch_model-
|
| 99 |
-
"model.layers.18.mlp.down_proj.weight": "pytorch_model-
|
| 100 |
-
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-
|
| 101 |
-
"model.layers.18.mlp.up_proj.weight": "pytorch_model-
|
| 102 |
-
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-
|
| 103 |
-
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-
|
| 104 |
-
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-
|
| 105 |
-
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-
|
| 106 |
-
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-
|
| 107 |
-
"model.layers.19.input_layernorm.weight": "pytorch_model-
|
| 108 |
-
"model.layers.19.mlp.down_proj.weight": "pytorch_model-
|
| 109 |
-
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-
|
| 110 |
-
"model.layers.19.mlp.up_proj.weight": "pytorch_model-
|
| 111 |
-
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-
|
| 112 |
-
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-
|
| 113 |
-
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-
|
| 114 |
-
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-
|
| 115 |
-
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-
|
| 116 |
-
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-
|
| 117 |
-
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 118 |
-
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 119 |
-
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 120 |
-
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 121 |
-
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 122 |
-
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 123 |
-
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 124 |
-
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 125 |
-
"model.layers.20.input_layernorm.weight": "pytorch_model-
|
| 126 |
-
"model.layers.20.mlp.down_proj.weight": "pytorch_model-
|
| 127 |
-
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-
|
| 128 |
-
"model.layers.20.mlp.up_proj.weight": "pytorch_model-
|
| 129 |
-
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-
|
| 130 |
-
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-
|
| 131 |
-
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-
|
| 132 |
-
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-
|
| 133 |
-
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-
|
| 134 |
-
"model.layers.21.input_layernorm.weight": "pytorch_model-
|
| 135 |
-
"model.layers.21.mlp.down_proj.weight": "pytorch_model-
|
| 136 |
-
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-
|
| 137 |
-
"model.layers.21.mlp.up_proj.weight": "pytorch_model-
|
| 138 |
-
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-
|
| 139 |
-
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-
|
| 140 |
-
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-
|
| 141 |
-
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-
|
| 142 |
-
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-
|
| 143 |
-
"model.layers.22.input_layernorm.weight": "pytorch_model-
|
| 144 |
-
"model.layers.22.mlp.down_proj.weight": "pytorch_model-
|
| 145 |
-
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-
|
| 146 |
-
"model.layers.22.mlp.up_proj.weight": "pytorch_model-
|
| 147 |
-
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-
|
| 148 |
-
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-
|
| 149 |
-
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-
|
| 150 |
-
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-
|
| 151 |
-
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-
|
| 152 |
-
"model.layers.23.input_layernorm.weight": "pytorch_model-
|
| 153 |
-
"model.layers.23.mlp.down_proj.weight": "pytorch_model-
|
| 154 |
-
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-
|
| 155 |
-
"model.layers.23.mlp.up_proj.weight": "pytorch_model-
|
| 156 |
-
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-
|
| 157 |
-
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-
|
| 158 |
-
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-
|
| 159 |
-
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-
|
| 160 |
-
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-
|
| 161 |
-
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-
|
| 162 |
-
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-
|
| 163 |
-
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-
|
| 164 |
-
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-
|
| 165 |
-
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-
|
| 166 |
-
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-
|
| 167 |
-
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-
|
| 168 |
-
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-
|
| 169 |
-
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-
|
| 170 |
-
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-
|
| 171 |
-
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-
|
| 172 |
-
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-
|
| 173 |
-
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-
|
| 174 |
-
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-
|
| 175 |
-
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-
|
| 176 |
-
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-
|
| 177 |
-
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-
|
| 178 |
-
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-
|
| 179 |
-
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-
|
| 180 |
-
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-
|
| 181 |
-
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-
|
| 182 |
-
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-
|
| 183 |
-
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-
|
| 184 |
-
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-
|
| 185 |
-
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-
|
| 186 |
-
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-
|
| 187 |
-
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-
|
| 188 |
-
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-
|
| 189 |
-
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-
|
| 190 |
-
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-
|
| 191 |
-
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-
|
| 192 |
-
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-
|
| 193 |
-
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-
|
| 194 |
-
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-
|
| 195 |
-
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-
|
| 196 |
-
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-
|
| 197 |
-
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-
|
| 198 |
-
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-
|
| 199 |
-
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-
|
| 200 |
-
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-
|
| 201 |
-
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-
|
| 202 |
-
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-
|
| 203 |
-
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-
|
| 204 |
-
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-
|
| 205 |
-
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-
|
| 206 |
-
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-
|
| 207 |
-
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-
|
| 208 |
-
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-
|
| 209 |
-
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-
|
| 210 |
-
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-
|
| 211 |
-
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-
|
| 212 |
-
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-
|
| 213 |
-
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-
|
| 214 |
-
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-
|
| 215 |
-
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-
|
| 216 |
-
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-
|
| 217 |
-
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-
|
| 218 |
-
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-
|
| 219 |
-
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-
|
| 220 |
-
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-
|
| 221 |
-
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-
|
| 222 |
-
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-
|
| 223 |
-
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-
|
| 224 |
-
"model.layers.30.input_layernorm.weight": "pytorch_model-
|
| 225 |
-
"model.layers.30.mlp.down_proj.weight": "pytorch_model-
|
| 226 |
-
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-
|
| 227 |
-
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-
|
| 228 |
-
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-
|
| 229 |
-
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-
|
| 230 |
-
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-
|
| 231 |
-
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-
|
| 232 |
-
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-
|
| 233 |
-
"model.layers.31.input_layernorm.weight": "pytorch_model-
|
| 234 |
-
"model.layers.31.mlp.down_proj.weight": "pytorch_model-
|
| 235 |
-
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-
|
| 236 |
-
"model.layers.31.mlp.up_proj.weight": "pytorch_model-
|
| 237 |
-
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-
|
| 238 |
-
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-
|
| 239 |
-
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-
|
| 240 |
-
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-
|
| 241 |
-
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-
|
| 242 |
-
"model.layers.
|
| 243 |
-
"model.layers.
|
| 244 |
-
"model.layers.
|
| 245 |
-
"model.layers.
|
| 246 |
-
"model.layers.
|
| 247 |
-
"model.layers.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.
|
| 252 |
-
"model.layers.
|
| 253 |
-
"model.layers.
|
| 254 |
-
"model.layers.
|
| 255 |
-
"model.layers.
|
| 256 |
-
"model.layers.
|
| 257 |
-
"model.layers.
|
| 258 |
-
"model.layers.
|
| 259 |
-
"model.layers.
|
| 260 |
-
"model.layers.
|
| 261 |
-
"model.layers.
|
| 262 |
-
"model.layers.
|
| 263 |
-
"model.layers.
|
| 264 |
-
"model.layers.
|
| 265 |
-
"model.layers.
|
| 266 |
-
"model.layers.
|
| 267 |
-
"model.layers.
|
| 268 |
-
"model.layers.
|
| 269 |
-
"model.layers.
|
| 270 |
-
"model.layers.
|
| 271 |
-
"model.layers.
|
| 272 |
-
"model.layers.
|
| 273 |
-
"model.layers.
|
| 274 |
-
"model.layers.
|
| 275 |
-
"model.layers.
|
| 276 |
-
"model.layers.
|
| 277 |
-
"model.layers.
|
| 278 |
-
"model.layers.
|
| 279 |
-
"model.layers.
|
| 280 |
-
"model.layers.
|
| 281 |
-
"model.layers.
|
| 282 |
-
"model.layers.
|
| 283 |
-
"model.layers.
|
| 284 |
-
"model.layers.
|
| 285 |
-
"model.layers.
|
| 286 |
-
"model.layers.
|
| 287 |
-
"model.layers.
|
| 288 |
-
"model.layers.
|
| 289 |
-
"model.layers.
|
| 290 |
-
"model.layers.
|
| 291 |
-
"model.layers.
|
| 292 |
-
"model.layers.
|
| 293 |
-
"model.layers.
|
| 294 |
-
"model.layers.
|
| 295 |
-
"model.layers.
|
| 296 |
-
"model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 297 |
}
|
| 298 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 26031728640
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 242 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 243 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 244 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 245 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 246 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 247 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 248 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 249 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 250 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 251 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 252 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 253 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 254 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 255 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 256 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 257 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 258 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 259 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 260 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 261 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 262 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 263 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 264 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 265 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 266 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 267 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 268 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 269 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 270 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 271 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 272 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 273 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 274 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 275 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 276 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 277 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 278 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 279 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 280 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 281 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 282 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 283 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 284 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 285 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 286 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 287 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 288 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 289 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 290 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 291 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 292 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 293 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 294 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 295 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 296 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 297 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 298 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 299 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 300 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 301 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 302 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 303 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 304 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 305 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 306 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 307 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 308 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 309 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 310 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 311 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 312 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 313 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 314 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 315 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 316 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 317 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 318 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 319 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 320 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 321 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 322 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 323 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 324 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 325 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 326 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 327 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 328 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 329 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 330 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 331 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 332 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 333 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 334 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 335 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 336 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 337 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 338 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 339 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 340 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 341 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 342 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 343 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 344 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 345 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 346 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 347 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 348 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 349 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 350 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 351 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 352 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 353 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 354 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 355 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 356 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 357 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 358 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 359 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 360 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 361 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 362 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 363 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 364 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 365 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 366 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 367 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 368 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
| 369 |
}
|
| 370 |
}
|
special_tokens_map.json
DELETED
|
@@ -1,24 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<s>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": "</s>",
|
| 17 |
-
"unk_token": {
|
| 18 |
-
"content": "<unk>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
DELETED
|
@@ -1,45 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": true,
|
| 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": "<s>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": false,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false,
|
| 19 |
-
"special": true
|
| 20 |
-
},
|
| 21 |
-
"2": {
|
| 22 |
-
"content": "</s>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false,
|
| 27 |
-
"special": true
|
| 28 |
-
}
|
| 29 |
-
},
|
| 30 |
-
"bos_token": "<s>",
|
| 31 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
| 32 |
-
"clean_up_tokenization_spaces": false,
|
| 33 |
-
"eos_token": "</s>",
|
| 34 |
-
"legacy": false,
|
| 35 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
-
"pad_token": "</s>",
|
| 37 |
-
"padding_side": "right",
|
| 38 |
-
"sp_model_kwargs": {},
|
| 39 |
-
"spaces_between_special_tokens": false,
|
| 40 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
-
"trust_remote_code": false,
|
| 42 |
-
"unk_token": "<unk>",
|
| 43 |
-
"use_default_system_prompt": true,
|
| 44 |
-
"use_fast": true
|
| 45 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.model → training_args.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c930ec54ee43d7d1627494a952d0865757392653d0746c43ebe1a9cfaa244ba
|
| 3 |
+
size 4475
|