Commit
•
d75a7c3
0
Parent(s):
Duplicate from HuggingFaceH4/starcoderbase-finetuned-oasst1
Browse files- .gitattributes +34 -0
- README.md +200 -0
- TRAINER_README.md +63 -0
- added_tokens.json +6 -0
- all_results.json +14 -0
- config.json +39 -0
- dialogue_template.json +8 -0
- eval_results.json +9 -0
- generation_config.json +6 -0
- handler.py +51 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +491 -0
- pytorch_model-00001-of-00004.bin +3 -0
- pytorch_model-00002-of-00004.bin +3 -0
- pytorch_model-00003-of-00004.bin +3 -0
- pytorch_model-00004-of-00004.bin +3 -0
- pytorch_model.bin.index.json +492 -0
- requirements.txt +5 -0
- runs/May01_16-15-57_ip-26-0-152-157/1682958072.5762024/events.out.tfevents.1682958072.ip-26-0-152-157.1125661.1 +3 -0
- runs/May01_16-15-57_ip-26-0-152-157/events.out.tfevents.1682958072.ip-26-0-152-157.1125661.0 +3 -0
- runs/May01_16-15-57_ip-26-0-152-157/events.out.tfevents.1682961184.ip-26-0-152-157.1125661.2 +3 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -0
- train_results.json +8 -0
- trainer_state.json +127 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,200 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bigcode-openrail-m
|
| 3 |
+
duplicated_from: HuggingFaceH4/starcoderbase-finetuned-oasst1
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for starcoderbase-finetuned-oasst1
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
|
| 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 |
+
|
TRAINER_README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: starcoder-ift
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# starcoder-ift
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [bigcode/large-model](https://huggingface.co/bigcode/large-model) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 1.4943
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 2e-05
|
| 36 |
+
- train_batch_size: 2
|
| 37 |
+
- eval_batch_size: 2
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 8
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 128
|
| 43 |
+
- total_eval_batch_size: 16
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
+
- num_epochs: 3
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 1.6668 | 0.99 | 65 | 1.6167 |
|
| 54 |
+
| 1.3584 | 2.0 | 131 | 1.5126 |
|
| 55 |
+
| 1.0949 | 2.98 | 195 | 1.4943 |
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
### Framework versions
|
| 59 |
+
|
| 60 |
+
- Transformers 4.28.1
|
| 61 |
+
- Pytorch 1.13.1+cu117
|
| 62 |
+
- Datasets 2.12.0
|
| 63 |
+
- Tokenizers 0.13.3
|
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|assistant|>": 49154,
|
| 3 |
+
"<|end|>": 49155,
|
| 4 |
+
"<|system|>": 49152,
|
| 5 |
+
"<|user|>": 49153
|
| 6 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"eval_loss": 1.4942539930343628,
|
| 4 |
+
"eval_runtime": 22.3723,
|
| 5 |
+
"eval_samples": 879,
|
| 6 |
+
"eval_samples_per_second": 39.29,
|
| 7 |
+
"eval_steps_per_second": 2.458,
|
| 8 |
+
"perplexity": 4.456011097278015,
|
| 9 |
+
"train_loss": 1.4244933299529248,
|
| 10 |
+
"train_runtime": 3089.4842,
|
| 11 |
+
"train_samples": 8372,
|
| 12 |
+
"train_samples_per_second": 8.13,
|
| 13 |
+
"train_steps_per_second": 0.063
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/fsx/h4/checkpoints/starchat",
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTBigCodeForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_softmax_in_fp32": true,
|
| 8 |
+
"attn_pdrop": 0.1,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 0,
|
| 12 |
+
"inference_runner": 0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"layer_norm_epsilon": 1e-05,
|
| 15 |
+
"max_batch_size": null,
|
| 16 |
+
"max_sequence_length": null,
|
| 17 |
+
"model_type": "gpt_bigcode",
|
| 18 |
+
"multi_query": true,
|
| 19 |
+
"n_embd": 6144,
|
| 20 |
+
"n_head": 48,
|
| 21 |
+
"n_inner": 24576,
|
| 22 |
+
"n_layer": 40,
|
| 23 |
+
"n_positions": 8192,
|
| 24 |
+
"pad_key_length": true,
|
| 25 |
+
"pre_allocate_kv_cache": false,
|
| 26 |
+
"resid_pdrop": 0.1,
|
| 27 |
+
"scale_attention_softmax_in_fp32": true,
|
| 28 |
+
"scale_attn_weights": true,
|
| 29 |
+
"summary_activation": null,
|
| 30 |
+
"summary_first_dropout": 0.1,
|
| 31 |
+
"summary_proj_to_labels": true,
|
| 32 |
+
"summary_type": "cls_index",
|
| 33 |
+
"summary_use_proj": true,
|
| 34 |
+
"torch_dtype": "float16",
|
| 35 |
+
"transformers_version": "4.28.1",
|
| 36 |
+
"use_cache": false,
|
| 37 |
+
"validate_runner_input": true,
|
| 38 |
+
"vocab_size": 49156
|
| 39 |
+
}
|
dialogue_template.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"system": "",
|
| 3 |
+
"messages": null,
|
| 4 |
+
"system_token": "<|system|>",
|
| 5 |
+
"user_token": "<|user|>",
|
| 6 |
+
"assistant_token": "<|assistant|>",
|
| 7 |
+
"end_token": "<|end|>"
|
| 8 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"eval_loss": 1.4942539930343628,
|
| 4 |
+
"eval_runtime": 22.3723,
|
| 5 |
+
"eval_samples": 879,
|
| 6 |
+
"eval_samples_per_second": 39.29,
|
| 7 |
+
"eval_steps_per_second": 2.458,
|
| 8 |
+
"perplexity": 4.456011097278015
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.28.1"
|
| 6 |
+
}
|
handler.py
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from typing import Any, Dict
|
| 2 |
+
|
| 3 |
+
import torch
|
| 4 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 5 |
+
|
| 6 |
+
from peft import PeftConfig, PeftModel
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
class EndpointHandler:
|
| 10 |
+
def __init__(self, path=""):
|
| 11 |
+
# load model and processor from path
|
| 12 |
+
self.tokenizer = AutoTokenizer.from_pretrained(path)
|
| 13 |
+
try:
|
| 14 |
+
config = PeftConfig.from_pretrained(path)
|
| 15 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 16 |
+
config.base_model_name_or_path,
|
| 17 |
+
return_dict=True,
|
| 18 |
+
load_in_8bit=True,
|
| 19 |
+
device_map="auto",
|
| 20 |
+
torch_dtype=torch.float16,
|
| 21 |
+
)
|
| 22 |
+
model.resize_token_embeddings(len(self.tokenizer))
|
| 23 |
+
model = PeftModel.from_pretrained(model, path)
|
| 24 |
+
except Exception:
|
| 25 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 26 |
+
path,
|
| 27 |
+
device_map="auto",
|
| 28 |
+
load_in_8bit=True,
|
| 29 |
+
torch_dtype=torch.float16,
|
| 30 |
+
)
|
| 31 |
+
self.model = model
|
| 32 |
+
self.device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 33 |
+
|
| 34 |
+
def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
|
| 35 |
+
# process input
|
| 36 |
+
inputs = data.pop("inputs", data)
|
| 37 |
+
parameters = data.pop("parameters", None)
|
| 38 |
+
|
| 39 |
+
# preprocess
|
| 40 |
+
inputs = self.tokenizer(inputs, return_tensors="pt").to(self.device)
|
| 41 |
+
|
| 42 |
+
# pass inputs with all kwargs in data
|
| 43 |
+
if parameters is not None:
|
| 44 |
+
outputs = self.model.generate(**inputs, **parameters)
|
| 45 |
+
else:
|
| 46 |
+
outputs = self.model.generate(**inputs)
|
| 47 |
+
|
| 48 |
+
# postprocess the prediction
|
| 49 |
+
prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 50 |
+
|
| 51 |
+
return [{"generated_text": prediction}]
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:566fe0b19d76fa6bbb734712f785aa1b65dc2a81236d7e1ec44e03a3e5458d5a
|
| 3 |
+
size 9957996824
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7de3d434adbf5e4fdd9be364dd9279280c6280d4c282bf54061db43b928bd51e
|
| 3 |
+
size 9857346184
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97958e2b94d55527cc4695539162c41825fff0a79dc22bc092dc4290de4802be
|
| 3 |
+
size 9857346184
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d27f63454f96f7458675b33544ab897b8b00a314ea5a87b7d25103e3e775fa5
|
| 3 |
+
size 1362323816
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,491 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 31034961920
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 7 |
+
"transformer.h.0.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 9 |
+
"transformer.h.0.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"transformer.h.0.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 11 |
+
"transformer.h.0.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"transformer.h.0.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 13 |
+
"transformer.h.0.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 15 |
+
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 17 |
+
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 19 |
+
"transformer.h.1.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 21 |
+
"transformer.h.1.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"transformer.h.1.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 23 |
+
"transformer.h.1.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"transformer.h.1.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 25 |
+
"transformer.h.1.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 27 |
+
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 29 |
+
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"transformer.h.10.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 31 |
+
"transformer.h.10.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 32 |
+
"transformer.h.10.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 33 |
+
"transformer.h.10.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 34 |
+
"transformer.h.10.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 35 |
+
"transformer.h.10.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 36 |
+
"transformer.h.10.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 37 |
+
"transformer.h.10.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 38 |
+
"transformer.h.10.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 39 |
+
"transformer.h.10.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 40 |
+
"transformer.h.10.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 41 |
+
"transformer.h.10.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 42 |
+
"transformer.h.11.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 43 |
+
"transformer.h.11.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 44 |
+
"transformer.h.11.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 45 |
+
"transformer.h.11.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 46 |
+
"transformer.h.11.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 47 |
+
"transformer.h.11.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 48 |
+
"transformer.h.11.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 49 |
+
"transformer.h.11.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 50 |
+
"transformer.h.11.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 51 |
+
"transformer.h.11.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 52 |
+
"transformer.h.11.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 53 |
+
"transformer.h.11.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 54 |
+
"transformer.h.12.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 55 |
+
"transformer.h.12.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 56 |
+
"transformer.h.12.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 57 |
+
"transformer.h.12.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 58 |
+
"transformer.h.12.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 59 |
+
"transformer.h.12.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 60 |
+
"transformer.h.12.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 61 |
+
"transformer.h.12.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 62 |
+
"transformer.h.12.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 63 |
+
"transformer.h.12.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"transformer.h.12.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 65 |
+
"transformer.h.12.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"transformer.h.13.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 67 |
+
"transformer.h.13.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"transformer.h.13.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 69 |
+
"transformer.h.13.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"transformer.h.13.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 71 |
+
"transformer.h.13.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"transformer.h.13.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 73 |
+
"transformer.h.13.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"transformer.h.13.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 75 |
+
"transformer.h.13.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"transformer.h.13.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 77 |
+
"transformer.h.13.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"transformer.h.14.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 79 |
+
"transformer.h.14.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"transformer.h.14.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 81 |
+
"transformer.h.14.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"transformer.h.14.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 83 |
+
"transformer.h.14.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"transformer.h.14.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 85 |
+
"transformer.h.14.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"transformer.h.14.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 87 |
+
"transformer.h.14.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"transformer.h.14.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 89 |
+
"transformer.h.14.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"transformer.h.15.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 91 |
+
"transformer.h.15.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"transformer.h.15.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 93 |
+
"transformer.h.15.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"transformer.h.15.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 95 |
+
"transformer.h.15.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"transformer.h.15.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 97 |
+
"transformer.h.15.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"transformer.h.15.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 99 |
+
"transformer.h.15.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"transformer.h.15.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 101 |
+
"transformer.h.15.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"transformer.h.16.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 103 |
+
"transformer.h.16.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"transformer.h.16.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 105 |
+
"transformer.h.16.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"transformer.h.16.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 107 |
+
"transformer.h.16.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"transformer.h.16.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 109 |
+
"transformer.h.16.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"transformer.h.16.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 111 |
+
"transformer.h.16.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"transformer.h.16.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 113 |
+
"transformer.h.16.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"transformer.h.17.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 115 |
+
"transformer.h.17.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"transformer.h.17.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 117 |
+
"transformer.h.17.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"transformer.h.17.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 119 |
+
"transformer.h.17.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"transformer.h.17.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 121 |
+
"transformer.h.17.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"transformer.h.17.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 123 |
+
"transformer.h.17.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"transformer.h.17.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 125 |
+
"transformer.h.17.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"transformer.h.18.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 127 |
+
"transformer.h.18.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"transformer.h.18.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 129 |
+
"transformer.h.18.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"transformer.h.18.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 131 |
+
"transformer.h.18.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"transformer.h.18.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 133 |
+
"transformer.h.18.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"transformer.h.18.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 135 |
+
"transformer.h.18.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"transformer.h.18.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 137 |
+
"transformer.h.18.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"transformer.h.19.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 139 |
+
"transformer.h.19.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"transformer.h.19.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 141 |
+
"transformer.h.19.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 142 |
+
"transformer.h.19.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 143 |
+
"transformer.h.19.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 144 |
+
"transformer.h.19.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 145 |
+
"transformer.h.19.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 146 |
+
"transformer.h.19.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 147 |
+
"transformer.h.19.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 148 |
+
"transformer.h.19.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 149 |
+
"transformer.h.19.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 150 |
+
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 151 |
+
"transformer.h.2.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 153 |
+
"transformer.h.2.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 154 |
+
"transformer.h.2.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 155 |
+
"transformer.h.2.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 156 |
+
"transformer.h.2.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 157 |
+
"transformer.h.2.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 158 |
+
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 159 |
+
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 160 |
+
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 161 |
+
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 162 |
+
"transformer.h.20.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 163 |
+
"transformer.h.20.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"transformer.h.20.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 165 |
+
"transformer.h.20.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"transformer.h.20.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 167 |
+
"transformer.h.20.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"transformer.h.20.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 169 |
+
"transformer.h.20.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"transformer.h.20.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 171 |
+
"transformer.h.20.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"transformer.h.20.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 173 |
+
"transformer.h.20.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"transformer.h.21.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 175 |
+
"transformer.h.21.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 176 |
+
"transformer.h.21.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 177 |
+
"transformer.h.21.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"transformer.h.21.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 179 |
+
"transformer.h.21.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"transformer.h.21.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 181 |
+
"transformer.h.21.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"transformer.h.21.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 183 |
+
"transformer.h.21.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"transformer.h.21.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 185 |
+
"transformer.h.21.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 186 |
+
"transformer.h.22.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 187 |
+
"transformer.h.22.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 188 |
+
"transformer.h.22.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 189 |
+
"transformer.h.22.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 190 |
+
"transformer.h.22.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 191 |
+
"transformer.h.22.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 192 |
+
"transformer.h.22.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 193 |
+
"transformer.h.22.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 194 |
+
"transformer.h.22.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 195 |
+
"transformer.h.22.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 196 |
+
"transformer.h.22.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 197 |
+
"transformer.h.22.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 198 |
+
"transformer.h.23.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 199 |
+
"transformer.h.23.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 200 |
+
"transformer.h.23.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 201 |
+
"transformer.h.23.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 202 |
+
"transformer.h.23.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 203 |
+
"transformer.h.23.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 204 |
+
"transformer.h.23.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 205 |
+
"transformer.h.23.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 206 |
+
"transformer.h.23.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 207 |
+
"transformer.h.23.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 208 |
+
"transformer.h.23.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 209 |
+
"transformer.h.23.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 210 |
+
"transformer.h.24.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 211 |
+
"transformer.h.24.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 212 |
+
"transformer.h.24.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 213 |
+
"transformer.h.24.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 214 |
+
"transformer.h.24.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 215 |
+
"transformer.h.24.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 216 |
+
"transformer.h.24.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 217 |
+
"transformer.h.24.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 218 |
+
"transformer.h.24.mlp.c_fc.bias": "model-00002-of-00004.safetensors",
|
| 219 |
+
"transformer.h.24.mlp.c_fc.weight": "model-00002-of-00004.safetensors",
|
| 220 |
+
"transformer.h.24.mlp.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 221 |
+
"transformer.h.24.mlp.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 222 |
+
"transformer.h.25.attn.c_attn.bias": "model-00002-of-00004.safetensors",
|
| 223 |
+
"transformer.h.25.attn.c_attn.weight": "model-00002-of-00004.safetensors",
|
| 224 |
+
"transformer.h.25.attn.c_proj.bias": "model-00002-of-00004.safetensors",
|
| 225 |
+
"transformer.h.25.attn.c_proj.weight": "model-00002-of-00004.safetensors",
|
| 226 |
+
"transformer.h.25.ln_1.bias": "model-00002-of-00004.safetensors",
|
| 227 |
+
"transformer.h.25.ln_1.weight": "model-00002-of-00004.safetensors",
|
| 228 |
+
"transformer.h.25.ln_2.bias": "model-00002-of-00004.safetensors",
|
| 229 |
+
"transformer.h.25.ln_2.weight": "model-00002-of-00004.safetensors",
|
| 230 |
+
"transformer.h.25.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 231 |
+
"transformer.h.25.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"transformer.h.25.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 233 |
+
"transformer.h.25.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"transformer.h.26.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 235 |
+
"transformer.h.26.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"transformer.h.26.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 237 |
+
"transformer.h.26.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"transformer.h.26.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 239 |
+
"transformer.h.26.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"transformer.h.26.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 241 |
+
"transformer.h.26.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"transformer.h.26.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 243 |
+
"transformer.h.26.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"transformer.h.26.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 245 |
+
"transformer.h.26.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"transformer.h.27.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 247 |
+
"transformer.h.27.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"transformer.h.27.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 249 |
+
"transformer.h.27.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"transformer.h.27.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 251 |
+
"transformer.h.27.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"transformer.h.27.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 253 |
+
"transformer.h.27.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"transformer.h.27.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 255 |
+
"transformer.h.27.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"transformer.h.27.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 257 |
+
"transformer.h.27.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"transformer.h.28.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 259 |
+
"transformer.h.28.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"transformer.h.28.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 261 |
+
"transformer.h.28.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"transformer.h.28.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 263 |
+
"transformer.h.28.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 264 |
+
"transformer.h.28.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 265 |
+
"transformer.h.28.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 266 |
+
"transformer.h.28.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 267 |
+
"transformer.h.28.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 268 |
+
"transformer.h.28.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 269 |
+
"transformer.h.28.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 270 |
+
"transformer.h.29.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 271 |
+
"transformer.h.29.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 272 |
+
"transformer.h.29.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 273 |
+
"transformer.h.29.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"transformer.h.29.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 275 |
+
"transformer.h.29.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"transformer.h.29.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 277 |
+
"transformer.h.29.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"transformer.h.29.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 279 |
+
"transformer.h.29.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"transformer.h.29.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 281 |
+
"transformer.h.29.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 283 |
+
"transformer.h.3.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 285 |
+
"transformer.h.3.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"transformer.h.3.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 287 |
+
"transformer.h.3.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"transformer.h.3.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 289 |
+
"transformer.h.3.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 290 |
+
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 291 |
+
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 292 |
+
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 293 |
+
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 294 |
+
"transformer.h.30.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 295 |
+
"transformer.h.30.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"transformer.h.30.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 297 |
+
"transformer.h.30.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"transformer.h.30.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 299 |
+
"transformer.h.30.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"transformer.h.30.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 301 |
+
"transformer.h.30.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"transformer.h.30.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 303 |
+
"transformer.h.30.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"transformer.h.30.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 305 |
+
"transformer.h.30.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"transformer.h.31.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 307 |
+
"transformer.h.31.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"transformer.h.31.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 309 |
+
"transformer.h.31.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"transformer.h.31.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 311 |
+
"transformer.h.31.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"transformer.h.31.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 313 |
+
"transformer.h.31.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"transformer.h.31.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 315 |
+
"transformer.h.31.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"transformer.h.31.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 317 |
+
"transformer.h.31.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"transformer.h.32.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 319 |
+
"transformer.h.32.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"transformer.h.32.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 321 |
+
"transformer.h.32.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"transformer.h.32.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 323 |
+
"transformer.h.32.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"transformer.h.32.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 325 |
+
"transformer.h.32.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"transformer.h.32.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 327 |
+
"transformer.h.32.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 328 |
+
"transformer.h.32.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 329 |
+
"transformer.h.32.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 330 |
+
"transformer.h.33.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 331 |
+
"transformer.h.33.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 332 |
+
"transformer.h.33.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 333 |
+
"transformer.h.33.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 334 |
+
"transformer.h.33.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 335 |
+
"transformer.h.33.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 336 |
+
"transformer.h.33.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 337 |
+
"transformer.h.33.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"transformer.h.33.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 339 |
+
"transformer.h.33.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 340 |
+
"transformer.h.33.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 341 |
+
"transformer.h.33.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 342 |
+
"transformer.h.34.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 343 |
+
"transformer.h.34.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 344 |
+
"transformer.h.34.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 345 |
+
"transformer.h.34.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 346 |
+
"transformer.h.34.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 347 |
+
"transformer.h.34.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 348 |
+
"transformer.h.34.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 349 |
+
"transformer.h.34.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 350 |
+
"transformer.h.34.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 351 |
+
"transformer.h.34.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 352 |
+
"transformer.h.34.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 353 |
+
"transformer.h.34.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 354 |
+
"transformer.h.35.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 355 |
+
"transformer.h.35.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 356 |
+
"transformer.h.35.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 357 |
+
"transformer.h.35.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 358 |
+
"transformer.h.35.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 359 |
+
"transformer.h.35.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 360 |
+
"transformer.h.35.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 361 |
+
"transformer.h.35.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 362 |
+
"transformer.h.35.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 363 |
+
"transformer.h.35.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 364 |
+
"transformer.h.35.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 365 |
+
"transformer.h.35.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 366 |
+
"transformer.h.36.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 367 |
+
"transformer.h.36.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 368 |
+
"transformer.h.36.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 369 |
+
"transformer.h.36.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 370 |
+
"transformer.h.36.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 371 |
+
"transformer.h.36.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 372 |
+
"transformer.h.36.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 373 |
+
"transformer.h.36.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 374 |
+
"transformer.h.36.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 375 |
+
"transformer.h.36.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 376 |
+
"transformer.h.36.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 377 |
+
"transformer.h.36.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 378 |
+
"transformer.h.37.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 379 |
+
"transformer.h.37.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 380 |
+
"transformer.h.37.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 381 |
+
"transformer.h.37.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 382 |
+
"transformer.h.37.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 383 |
+
"transformer.h.37.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 384 |
+
"transformer.h.37.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 385 |
+
"transformer.h.37.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 386 |
+
"transformer.h.37.mlp.c_fc.bias": "model-00003-of-00004.safetensors",
|
| 387 |
+
"transformer.h.37.mlp.c_fc.weight": "model-00003-of-00004.safetensors",
|
| 388 |
+
"transformer.h.37.mlp.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 389 |
+
"transformer.h.37.mlp.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 390 |
+
"transformer.h.38.attn.c_attn.bias": "model-00003-of-00004.safetensors",
|
| 391 |
+
"transformer.h.38.attn.c_attn.weight": "model-00003-of-00004.safetensors",
|
| 392 |
+
"transformer.h.38.attn.c_proj.bias": "model-00003-of-00004.safetensors",
|
| 393 |
+
"transformer.h.38.attn.c_proj.weight": "model-00003-of-00004.safetensors",
|
| 394 |
+
"transformer.h.38.ln_1.bias": "model-00003-of-00004.safetensors",
|
| 395 |
+
"transformer.h.38.ln_1.weight": "model-00003-of-00004.safetensors",
|
| 396 |
+
"transformer.h.38.ln_2.bias": "model-00003-of-00004.safetensors",
|
| 397 |
+
"transformer.h.38.ln_2.weight": "model-00003-of-00004.safetensors",
|
| 398 |
+
"transformer.h.38.mlp.c_fc.bias": "model-00004-of-00004.safetensors",
|
| 399 |
+
"transformer.h.38.mlp.c_fc.weight": "model-00004-of-00004.safetensors",
|
| 400 |
+
"transformer.h.38.mlp.c_proj.bias": "model-00004-of-00004.safetensors",
|
| 401 |
+
"transformer.h.38.mlp.c_proj.weight": "model-00004-of-00004.safetensors",
|
| 402 |
+
"transformer.h.39.attn.c_attn.bias": "model-00004-of-00004.safetensors",
|
| 403 |
+
"transformer.h.39.attn.c_attn.weight": "model-00004-of-00004.safetensors",
|
| 404 |
+
"transformer.h.39.attn.c_proj.bias": "model-00004-of-00004.safetensors",
|
| 405 |
+
"transformer.h.39.attn.c_proj.weight": "model-00004-of-00004.safetensors",
|
| 406 |
+
"transformer.h.39.ln_1.bias": "model-00004-of-00004.safetensors",
|
| 407 |
+
"transformer.h.39.ln_1.weight": "model-00004-of-00004.safetensors",
|
| 408 |
+
"transformer.h.39.ln_2.bias": "model-00004-of-00004.safetensors",
|
| 409 |
+
"transformer.h.39.ln_2.weight": "model-00004-of-00004.safetensors",
|
| 410 |
+
"transformer.h.39.mlp.c_fc.bias": "model-00004-of-00004.safetensors",
|
| 411 |
+
"transformer.h.39.mlp.c_fc.weight": "model-00004-of-00004.safetensors",
|
| 412 |
+
"transformer.h.39.mlp.c_proj.bias": "model-00004-of-00004.safetensors",
|
| 413 |
+
"transformer.h.39.mlp.c_proj.weight": "model-00004-of-00004.safetensors",
|
| 414 |
+
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"transformer.h.4.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 417 |
+
"transformer.h.4.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"transformer.h.4.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 419 |
+
"transformer.h.4.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"transformer.h.4.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 421 |
+
"transformer.h.4.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"transformer.h.4.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"transformer.h.5.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"transformer.h.5.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"transformer.h.5.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 429 |
+
"transformer.h.5.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"transformer.h.5.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 431 |
+
"transformer.h.5.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"transformer.h.5.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 433 |
+
"transformer.h.5.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"transformer.h.5.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"transformer.h.5.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"transformer.h.5.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"transformer.h.6.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"transformer.h.6.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"transformer.h.6.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 441 |
+
"transformer.h.6.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"transformer.h.6.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"transformer.h.6.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"transformer.h.6.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"transformer.h.6.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"transformer.h.6.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"transformer.h.6.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"transformer.h.6.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"transformer.h.6.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"transformer.h.7.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"transformer.h.7.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"transformer.h.7.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 453 |
+
"transformer.h.7.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"transformer.h.7.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"transformer.h.7.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"transformer.h.7.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"transformer.h.7.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"transformer.h.7.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"transformer.h.7.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"transformer.h.7.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"transformer.h.7.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"transformer.h.8.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"transformer.h.8.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"transformer.h.8.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 465 |
+
"transformer.h.8.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"transformer.h.8.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"transformer.h.8.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"transformer.h.8.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"transformer.h.8.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"transformer.h.8.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"transformer.h.8.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"transformer.h.8.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"transformer.h.8.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"transformer.h.9.attn.c_attn.bias": "model-00001-of-00004.safetensors",
|
| 475 |
+
"transformer.h.9.attn.c_attn.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"transformer.h.9.attn.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 477 |
+
"transformer.h.9.attn.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"transformer.h.9.ln_1.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"transformer.h.9.ln_1.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"transformer.h.9.ln_2.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"transformer.h.9.ln_2.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"transformer.h.9.mlp.c_fc.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"transformer.h.9.mlp.c_fc.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"transformer.h.9.mlp.c_proj.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"transformer.h.9.mlp.c_proj.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"transformer.ln_f.bias": "model-00004-of-00004.safetensors",
|
| 487 |
+
"transformer.ln_f.weight": "model-00004-of-00004.safetensors",
|
| 488 |
+
"transformer.wpe.weight": "model-00001-of-00004.safetensors",
|
| 489 |
+
"transformer.wte.weight": "model-00001-of-00004.safetensors"
|
| 490 |
+
}
|
| 491 |
+
}
|
pytorch_model-00001-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4247f52857bfb61e4d87ebc898cfb07d87ddceed23c8f373c53fb56dcdd32f1e
|
| 3 |
+
size 9958032053
|
pytorch_model-00002-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88041f39fe07049e15a4afeaeadc061bf5c9e24307c49c722604b834e8025ed6
|
| 3 |
+
size 9857381671
|
pytorch_model-00003-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:756d6d98d2cadf58bc838269c041c416e82d3956c6d6fc4c9cae240f0f86f9b4
|
| 3 |
+
size 9857381671
|
pytorch_model-00004-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b16ef0cb635704577e3fc7c55d83871a3c1c1e71c04bfabaa2fa54499afe3b1
|
| 3 |
+
size 1966357157
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,492 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 31638990848
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
| 7 |
+
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 8 |
+
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 9 |
+
"transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 10 |
+
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 11 |
+
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 12 |
+
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 13 |
+
"transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 14 |
+
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 15 |
+
"transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 16 |
+
"transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 17 |
+
"transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 18 |
+
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 19 |
+
"transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 20 |
+
"transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 21 |
+
"transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 22 |
+
"transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 23 |
+
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 24 |
+
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 25 |
+
"transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 26 |
+
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 27 |
+
"transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 28 |
+
"transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 29 |
+
"transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 30 |
+
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 31 |
+
"transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 32 |
+
"transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 33 |
+
"transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 34 |
+
"transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 35 |
+
"transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 36 |
+
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 37 |
+
"transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 38 |
+
"transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 39 |
+
"transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 40 |
+
"transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 41 |
+
"transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 42 |
+
"transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 43 |
+
"transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 44 |
+
"transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 45 |
+
"transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 46 |
+
"transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 47 |
+
"transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 48 |
+
"transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 49 |
+
"transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 50 |
+
"transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 51 |
+
"transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 52 |
+
"transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 53 |
+
"transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 54 |
+
"transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 55 |
+
"transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 56 |
+
"transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 57 |
+
"transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 58 |
+
"transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 59 |
+
"transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 60 |
+
"transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 61 |
+
"transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 62 |
+
"transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 63 |
+
"transformer.h.12.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 64 |
+
"transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 65 |
+
"transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 66 |
+
"transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 67 |
+
"transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 68 |
+
"transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 69 |
+
"transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 70 |
+
"transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 71 |
+
"transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 72 |
+
"transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 73 |
+
"transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 74 |
+
"transformer.h.13.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 75 |
+
"transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 76 |
+
"transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 77 |
+
"transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 78 |
+
"transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 79 |
+
"transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 80 |
+
"transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 81 |
+
"transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 82 |
+
"transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 83 |
+
"transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 84 |
+
"transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 85 |
+
"transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 86 |
+
"transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 87 |
+
"transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 88 |
+
"transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 89 |
+
"transformer.h.14.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 90 |
+
"transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 91 |
+
"transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 92 |
+
"transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 93 |
+
"transformer.h.15.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 94 |
+
"transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 95 |
+
"transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 96 |
+
"transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 97 |
+
"transformer.h.15.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 98 |
+
"transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 99 |
+
"transformer.h.15.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 100 |
+
"transformer.h.15.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 101 |
+
"transformer.h.15.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 102 |
+
"transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 103 |
+
"transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 104 |
+
"transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 105 |
+
"transformer.h.16.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 106 |
+
"transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 107 |
+
"transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 108 |
+
"transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 109 |
+
"transformer.h.16.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 110 |
+
"transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 111 |
+
"transformer.h.16.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 112 |
+
"transformer.h.16.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 113 |
+
"transformer.h.16.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 114 |
+
"transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 115 |
+
"transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 116 |
+
"transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 117 |
+
"transformer.h.17.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 118 |
+
"transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 119 |
+
"transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 120 |
+
"transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 121 |
+
"transformer.h.17.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 122 |
+
"transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 123 |
+
"transformer.h.17.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 124 |
+
"transformer.h.17.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 125 |
+
"transformer.h.17.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 126 |
+
"transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 127 |
+
"transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 128 |
+
"transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 129 |
+
"transformer.h.18.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 130 |
+
"transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 131 |
+
"transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 132 |
+
"transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 133 |
+
"transformer.h.18.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 134 |
+
"transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 135 |
+
"transformer.h.18.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 136 |
+
"transformer.h.18.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 137 |
+
"transformer.h.18.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 138 |
+
"transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 139 |
+
"transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 140 |
+
"transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 141 |
+
"transformer.h.19.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 142 |
+
"transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 143 |
+
"transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 144 |
+
"transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 145 |
+
"transformer.h.19.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 146 |
+
"transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 147 |
+
"transformer.h.19.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 148 |
+
"transformer.h.19.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 149 |
+
"transformer.h.19.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 150 |
+
"transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 151 |
+
"transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 152 |
+
"transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 153 |
+
"transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 154 |
+
"transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 155 |
+
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 156 |
+
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 157 |
+
"transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 158 |
+
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 159 |
+
"transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 160 |
+
"transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 161 |
+
"transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 162 |
+
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 163 |
+
"transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 164 |
+
"transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 165 |
+
"transformer.h.20.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 166 |
+
"transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 167 |
+
"transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 168 |
+
"transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 169 |
+
"transformer.h.20.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 170 |
+
"transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 171 |
+
"transformer.h.20.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 172 |
+
"transformer.h.20.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 173 |
+
"transformer.h.20.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 174 |
+
"transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 175 |
+
"transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 176 |
+
"transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 177 |
+
"transformer.h.21.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 178 |
+
"transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 179 |
+
"transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 180 |
+
"transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 181 |
+
"transformer.h.21.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 182 |
+
"transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 183 |
+
"transformer.h.21.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 184 |
+
"transformer.h.21.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 185 |
+
"transformer.h.21.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 186 |
+
"transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 187 |
+
"transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 188 |
+
"transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 189 |
+
"transformer.h.22.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 190 |
+
"transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 191 |
+
"transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 192 |
+
"transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 193 |
+
"transformer.h.22.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 194 |
+
"transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 195 |
+
"transformer.h.22.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 196 |
+
"transformer.h.22.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 197 |
+
"transformer.h.22.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 198 |
+
"transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 199 |
+
"transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 200 |
+
"transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 201 |
+
"transformer.h.23.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 202 |
+
"transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 203 |
+
"transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 204 |
+
"transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 205 |
+
"transformer.h.23.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 206 |
+
"transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 207 |
+
"transformer.h.23.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 208 |
+
"transformer.h.23.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 209 |
+
"transformer.h.23.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 210 |
+
"transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 211 |
+
"transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 212 |
+
"transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 213 |
+
"transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 214 |
+
"transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 215 |
+
"transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 216 |
+
"transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 217 |
+
"transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 218 |
+
"transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 219 |
+
"transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
| 220 |
+
"transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
| 221 |
+
"transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 222 |
+
"transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 223 |
+
"transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
| 224 |
+
"transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
| 225 |
+
"transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
| 226 |
+
"transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 227 |
+
"transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
| 228 |
+
"transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
| 229 |
+
"transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
| 230 |
+
"transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
| 231 |
+
"transformer.h.25.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 232 |
+
"transformer.h.25.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 233 |
+
"transformer.h.25.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 234 |
+
"transformer.h.25.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 235 |
+
"transformer.h.26.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 236 |
+
"transformer.h.26.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 237 |
+
"transformer.h.26.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 238 |
+
"transformer.h.26.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 239 |
+
"transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 240 |
+
"transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 241 |
+
"transformer.h.26.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 242 |
+
"transformer.h.26.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 243 |
+
"transformer.h.26.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 244 |
+
"transformer.h.26.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 245 |
+
"transformer.h.26.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 246 |
+
"transformer.h.26.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 247 |
+
"transformer.h.27.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 248 |
+
"transformer.h.27.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 249 |
+
"transformer.h.27.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 250 |
+
"transformer.h.27.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 251 |
+
"transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 252 |
+
"transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 253 |
+
"transformer.h.27.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 254 |
+
"transformer.h.27.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 255 |
+
"transformer.h.27.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 256 |
+
"transformer.h.27.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 257 |
+
"transformer.h.27.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 258 |
+
"transformer.h.27.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 259 |
+
"transformer.h.28.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 260 |
+
"transformer.h.28.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 261 |
+
"transformer.h.28.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 262 |
+
"transformer.h.28.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 263 |
+
"transformer.h.28.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 264 |
+
"transformer.h.28.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 265 |
+
"transformer.h.28.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 266 |
+
"transformer.h.28.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 267 |
+
"transformer.h.28.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 268 |
+
"transformer.h.28.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 269 |
+
"transformer.h.28.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 270 |
+
"transformer.h.28.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 271 |
+
"transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 272 |
+
"transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 273 |
+
"transformer.h.29.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 274 |
+
"transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 275 |
+
"transformer.h.29.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 276 |
+
"transformer.h.29.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 277 |
+
"transformer.h.29.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 278 |
+
"transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 279 |
+
"transformer.h.29.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 280 |
+
"transformer.h.29.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 281 |
+
"transformer.h.29.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 282 |
+
"transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 283 |
+
"transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 284 |
+
"transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 285 |
+
"transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 286 |
+
"transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 287 |
+
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 288 |
+
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 289 |
+
"transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 290 |
+
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 291 |
+
"transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 292 |
+
"transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 293 |
+
"transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 294 |
+
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 295 |
+
"transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 296 |
+
"transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 297 |
+
"transformer.h.30.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 298 |
+
"transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 299 |
+
"transformer.h.30.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 300 |
+
"transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 301 |
+
"transformer.h.30.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 302 |
+
"transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 303 |
+
"transformer.h.30.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 304 |
+
"transformer.h.30.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 305 |
+
"transformer.h.30.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 306 |
+
"transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 307 |
+
"transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 308 |
+
"transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 309 |
+
"transformer.h.31.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 310 |
+
"transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 311 |
+
"transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 312 |
+
"transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 313 |
+
"transformer.h.31.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 314 |
+
"transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 315 |
+
"transformer.h.31.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 316 |
+
"transformer.h.31.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 317 |
+
"transformer.h.31.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 318 |
+
"transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 319 |
+
"transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 320 |
+
"transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 321 |
+
"transformer.h.32.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 322 |
+
"transformer.h.32.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 323 |
+
"transformer.h.32.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 324 |
+
"transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 325 |
+
"transformer.h.32.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 326 |
+
"transformer.h.32.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 327 |
+
"transformer.h.32.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 328 |
+
"transformer.h.32.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 329 |
+
"transformer.h.32.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 330 |
+
"transformer.h.32.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 331 |
+
"transformer.h.33.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 332 |
+
"transformer.h.33.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 333 |
+
"transformer.h.33.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 334 |
+
"transformer.h.33.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 335 |
+
"transformer.h.33.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 336 |
+
"transformer.h.33.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 337 |
+
"transformer.h.33.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 338 |
+
"transformer.h.33.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 339 |
+
"transformer.h.33.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 340 |
+
"transformer.h.33.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 341 |
+
"transformer.h.33.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 342 |
+
"transformer.h.33.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 343 |
+
"transformer.h.34.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 344 |
+
"transformer.h.34.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 345 |
+
"transformer.h.34.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 346 |
+
"transformer.h.34.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 347 |
+
"transformer.h.34.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 348 |
+
"transformer.h.34.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 349 |
+
"transformer.h.34.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 350 |
+
"transformer.h.34.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 351 |
+
"transformer.h.34.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 352 |
+
"transformer.h.34.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 353 |
+
"transformer.h.34.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 354 |
+
"transformer.h.34.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 355 |
+
"transformer.h.35.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 356 |
+
"transformer.h.35.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 357 |
+
"transformer.h.35.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 358 |
+
"transformer.h.35.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 359 |
+
"transformer.h.35.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 360 |
+
"transformer.h.35.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 361 |
+
"transformer.h.35.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 362 |
+
"transformer.h.35.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 363 |
+
"transformer.h.35.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 364 |
+
"transformer.h.35.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 365 |
+
"transformer.h.35.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 366 |
+
"transformer.h.35.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 367 |
+
"transformer.h.36.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 368 |
+
"transformer.h.36.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 369 |
+
"transformer.h.36.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 370 |
+
"transformer.h.36.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 371 |
+
"transformer.h.36.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 372 |
+
"transformer.h.36.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 373 |
+
"transformer.h.36.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 374 |
+
"transformer.h.36.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 375 |
+
"transformer.h.36.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 376 |
+
"transformer.h.36.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 377 |
+
"transformer.h.36.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 378 |
+
"transformer.h.36.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 379 |
+
"transformer.h.37.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 380 |
+
"transformer.h.37.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 381 |
+
"transformer.h.37.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 382 |
+
"transformer.h.37.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 383 |
+
"transformer.h.37.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 384 |
+
"transformer.h.37.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 385 |
+
"transformer.h.37.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 386 |
+
"transformer.h.37.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 387 |
+
"transformer.h.37.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
| 388 |
+
"transformer.h.37.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
| 389 |
+
"transformer.h.37.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 390 |
+
"transformer.h.37.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 391 |
+
"transformer.h.38.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
| 392 |
+
"transformer.h.38.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
| 393 |
+
"transformer.h.38.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
| 394 |
+
"transformer.h.38.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 395 |
+
"transformer.h.38.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
| 396 |
+
"transformer.h.38.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
| 397 |
+
"transformer.h.38.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
| 398 |
+
"transformer.h.38.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
| 399 |
+
"transformer.h.38.mlp.c_fc.bias": "pytorch_model-00004-of-00004.bin",
|
| 400 |
+
"transformer.h.38.mlp.c_fc.weight": "pytorch_model-00004-of-00004.bin",
|
| 401 |
+
"transformer.h.38.mlp.c_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 402 |
+
"transformer.h.38.mlp.c_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 403 |
+
"transformer.h.39.attn.c_attn.bias": "pytorch_model-00004-of-00004.bin",
|
| 404 |
+
"transformer.h.39.attn.c_attn.weight": "pytorch_model-00004-of-00004.bin",
|
| 405 |
+
"transformer.h.39.attn.c_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 406 |
+
"transformer.h.39.attn.c_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 407 |
+
"transformer.h.39.ln_1.bias": "pytorch_model-00004-of-00004.bin",
|
| 408 |
+
"transformer.h.39.ln_1.weight": "pytorch_model-00004-of-00004.bin",
|
| 409 |
+
"transformer.h.39.ln_2.bias": "pytorch_model-00004-of-00004.bin",
|
| 410 |
+
"transformer.h.39.ln_2.weight": "pytorch_model-00004-of-00004.bin",
|
| 411 |
+
"transformer.h.39.mlp.c_fc.bias": "pytorch_model-00004-of-00004.bin",
|
| 412 |
+
"transformer.h.39.mlp.c_fc.weight": "pytorch_model-00004-of-00004.bin",
|
| 413 |
+
"transformer.h.39.mlp.c_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 414 |
+
"transformer.h.39.mlp.c_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 415 |
+
"transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 416 |
+
"transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 417 |
+
"transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 418 |
+
"transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 419 |
+
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 420 |
+
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 421 |
+
"transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 422 |
+
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 423 |
+
"transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 424 |
+
"transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 425 |
+
"transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 426 |
+
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 427 |
+
"transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 428 |
+
"transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 429 |
+
"transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 430 |
+
"transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 431 |
+
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 432 |
+
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 433 |
+
"transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 434 |
+
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 435 |
+
"transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 436 |
+
"transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 437 |
+
"transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 438 |
+
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 439 |
+
"transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 440 |
+
"transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 441 |
+
"transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 442 |
+
"transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 443 |
+
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 444 |
+
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 445 |
+
"transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 446 |
+
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 447 |
+
"transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 448 |
+
"transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 449 |
+
"transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 450 |
+
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 451 |
+
"transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 452 |
+
"transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 453 |
+
"transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 454 |
+
"transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 455 |
+
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 456 |
+
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 457 |
+
"transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 458 |
+
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 459 |
+
"transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 460 |
+
"transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 461 |
+
"transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 462 |
+
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 463 |
+
"transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 464 |
+
"transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 465 |
+
"transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 466 |
+
"transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 467 |
+
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 468 |
+
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 469 |
+
"transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 470 |
+
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 471 |
+
"transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 472 |
+
"transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 473 |
+
"transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 474 |
+
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 475 |
+
"transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
| 476 |
+
"transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
| 477 |
+
"transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 478 |
+
"transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 479 |
+
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
| 480 |
+
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
| 481 |
+
"transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
| 482 |
+
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
| 483 |
+
"transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
| 484 |
+
"transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
| 485 |
+
"transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
| 486 |
+
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 487 |
+
"transformer.ln_f.bias": "pytorch_model-00004-of-00004.bin",
|
| 488 |
+
"transformer.ln_f.weight": "pytorch_model-00004-of-00004.bin",
|
| 489 |
+
"transformer.wpe.weight": "pytorch_model-00001-of-00004.bin",
|
| 490 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00004.bin"
|
| 491 |
+
}
|
| 492 |
+
}
|
requirements.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
transformers==4.28.1
|
| 2 |
+
accelerate>=0.16.0
|
| 3 |
+
bitsandbytes
|
| 4 |
+
sentencepiece
|
| 5 |
+
git+https://github.com/huggingface/peft.git@632997d1fb776c3cf05d8c2537ac9a98a7ce9435
|
runs/May01_16-15-57_ip-26-0-152-157/1682958072.5762024/events.out.tfevents.1682958072.ip-26-0-152-157.1125661.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f04b5bbd48a663aabbded48635c4b275d6722bc90830f66b12c6cf6f3e47c7d
|
| 3 |
+
size 6305
|
runs/May01_16-15-57_ip-26-0-152-157/events.out.tfevents.1682958072.ip-26-0-152-157.1125661.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13de7c986493d0eea6639c3159d1c11f91b3ef2cfbd604d29a5e894efd1ed1e9
|
| 3 |
+
size 7809
|
runs/May01_16-15-57_ip-26-0-152-157/events.out.tfevents.1682961184.ip-26-0-152-157.1125661.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f92f7b38a6da7e6680f20c416455c2d6ef953fb3f5d2420cdc600fdb582729d8
|
| 3 |
+
size 359
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|system|>",
|
| 4 |
+
"<|user|>",
|
| 5 |
+
"<|assistant|>",
|
| 6 |
+
"<|end|>"
|
| 7 |
+
],
|
| 8 |
+
"bos_token": "<|endoftext|>",
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"unk_token": "<|endoftext|>"
|
| 11 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"additional_special_tokens": [
|
| 4 |
+
"<|endoftext|>",
|
| 5 |
+
"<fim_prefix>",
|
| 6 |
+
"<fim_middle>",
|
| 7 |
+
"<fim_suffix>",
|
| 8 |
+
"<fim_pad>",
|
| 9 |
+
"<filename>",
|
| 10 |
+
"<gh_stars>",
|
| 11 |
+
"<issue_start>",
|
| 12 |
+
"<issue_comment>",
|
| 13 |
+
"<issue_closed>",
|
| 14 |
+
"<jupyter_start>",
|
| 15 |
+
"<jupyter_text>",
|
| 16 |
+
"<jupyter_code>",
|
| 17 |
+
"<jupyter_output>",
|
| 18 |
+
"<empty_output>",
|
| 19 |
+
"<commit_before>",
|
| 20 |
+
"<commit_msg>",
|
| 21 |
+
"<commit_after>",
|
| 22 |
+
"<reponame>"
|
| 23 |
+
],
|
| 24 |
+
"bos_token": "<|endoftext|>",
|
| 25 |
+
"clean_up_tokenization_spaces": true,
|
| 26 |
+
"eos_token": "<|endoftext|>",
|
| 27 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 29 |
+
"unk_token": "<|endoftext|>",
|
| 30 |
+
"vocab_size": 49152
|
| 31 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.98,
|
| 3 |
+
"train_loss": 1.4244933299529248,
|
| 4 |
+
"train_runtime": 3089.4842,
|
| 5 |
+
"train_samples": 8372,
|
| 6 |
+
"train_samples_per_second": 8.13,
|
| 7 |
+
"train_steps_per_second": 0.063
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9770992366412212,
|
| 5 |
+
"global_step": 195,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 0.0,
|
| 13 |
+
"loss": 2.2517,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.24,
|
| 18 |
+
"learning_rate": 2e-05,
|
| 19 |
+
"loss": 1.9184,
|
| 20 |
+
"step": 16
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.49,
|
| 24 |
+
"learning_rate": 2e-05,
|
| 25 |
+
"loss": 1.7725,
|
| 26 |
+
"step": 32
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.73,
|
| 30 |
+
"learning_rate": 2e-05,
|
| 31 |
+
"loss": 1.7075,
|
| 32 |
+
"step": 48
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.98,
|
| 36 |
+
"learning_rate": 2e-05,
|
| 37 |
+
"loss": 1.6668,
|
| 38 |
+
"step": 64
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.99,
|
| 42 |
+
"eval_loss": 1.6166764497756958,
|
| 43 |
+
"eval_runtime": 22.5473,
|
| 44 |
+
"eval_samples_per_second": 38.985,
|
| 45 |
+
"eval_steps_per_second": 2.439,
|
| 46 |
+
"step": 65
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.22,
|
| 50 |
+
"learning_rate": 2e-05,
|
| 51 |
+
"loss": 1.4567,
|
| 52 |
+
"step": 80
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.47,
|
| 56 |
+
"learning_rate": 2e-05,
|
| 57 |
+
"loss": 1.4109,
|
| 58 |
+
"step": 96
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.71,
|
| 62 |
+
"learning_rate": 2e-05,
|
| 63 |
+
"loss": 1.3875,
|
| 64 |
+
"step": 112
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.95,
|
| 68 |
+
"learning_rate": 2e-05,
|
| 69 |
+
"loss": 1.3584,
|
| 70 |
+
"step": 128
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.0,
|
| 74 |
+
"eval_loss": 1.512587547302246,
|
| 75 |
+
"eval_runtime": 22.5311,
|
| 76 |
+
"eval_samples_per_second": 39.013,
|
| 77 |
+
"eval_steps_per_second": 2.441,
|
| 78 |
+
"step": 131
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.2,
|
| 82 |
+
"learning_rate": 2e-05,
|
| 83 |
+
"loss": 1.1651,
|
| 84 |
+
"step": 144
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.44,
|
| 88 |
+
"learning_rate": 2e-05,
|
| 89 |
+
"loss": 1.1092,
|
| 90 |
+
"step": 160
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.69,
|
| 94 |
+
"learning_rate": 2e-05,
|
| 95 |
+
"loss": 1.0948,
|
| 96 |
+
"step": 176
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.93,
|
| 100 |
+
"learning_rate": 2e-05,
|
| 101 |
+
"loss": 1.0949,
|
| 102 |
+
"step": 192
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.98,
|
| 106 |
+
"eval_loss": 1.4942539930343628,
|
| 107 |
+
"eval_runtime": 22.489,
|
| 108 |
+
"eval_samples_per_second": 39.086,
|
| 109 |
+
"eval_steps_per_second": 2.446,
|
| 110 |
+
"step": 195
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.98,
|
| 114 |
+
"step": 195,
|
| 115 |
+
"total_flos": 417490551177216.0,
|
| 116 |
+
"train_loss": 1.4244933299529248,
|
| 117 |
+
"train_runtime": 3089.4842,
|
| 118 |
+
"train_samples_per_second": 8.13,
|
| 119 |
+
"train_steps_per_second": 0.063
|
| 120 |
+
}
|
| 121 |
+
],
|
| 122 |
+
"max_steps": 195,
|
| 123 |
+
"num_train_epochs": 3,
|
| 124 |
+
"total_flos": 417490551177216.0,
|
| 125 |
+
"trial_name": null,
|
| 126 |
+
"trial_params": null
|
| 127 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d8f2bb4f7ded48c54feaaf417fab68eb49470cdcc11bde02d559bf5b1e45582
|
| 3 |
+
size 4987
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|