Upload folder using huggingface_hub
Browse files- README.md +44 -0
- added_tokens.json +40 -0
- checkpoint-735/README.md +202 -0
- checkpoint-735/adapter_config.json +33 -0
- checkpoint-735/adapter_model.safetensors +3 -0
- checkpoint-735/added_tokens.json +40 -0
- checkpoint-735/merges.txt +0 -0
- checkpoint-735/optimizer.pt +3 -0
- checkpoint-735/pytorch_model.bin +3 -0
- checkpoint-735/rng_state.pth +3 -0
- checkpoint-735/scheduler.pt +3 -0
- checkpoint-735/special_tokens_map.json +24 -0
- checkpoint-735/tokenizer.json +0 -0
- checkpoint-735/tokenizer_config.json +325 -0
- checkpoint-735/trainer_state.json +224 -0
- checkpoint-735/training_args.bin +3 -0
- checkpoint-735/vocab.json +0 -0
- config.json +34 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +460 -0
- runs/Mar22_16-13-59_r-ambrosfitz-autotrain2-tunwm0pq-81bca-4nl3c/events.out.tfevents.1711124043.r-ambrosfitz-autotrain2-tunwm0pq-81bca-4nl3c.53.0 +2 -2
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +325 -0
- training_args.bin +3 -0
- training_params.json +47 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- autotrain
|
| 4 |
+
- text-generation
|
| 5 |
+
- peft
|
| 6 |
+
library_name: transformers
|
| 7 |
+
widget:
|
| 8 |
+
- messages:
|
| 9 |
+
- role: user
|
| 10 |
+
content: What is your favorite condiment?
|
| 11 |
+
license: other
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Model Trained Using AutoTrain
|
| 15 |
+
|
| 16 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
| 17 |
+
|
| 18 |
+
# Usage
|
| 19 |
+
|
| 20 |
+
```python
|
| 21 |
+
|
| 22 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 23 |
+
|
| 24 |
+
model_path = "PATH_TO_THIS_REPO"
|
| 25 |
+
|
| 26 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 27 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 28 |
+
model_path,
|
| 29 |
+
device_map="auto",
|
| 30 |
+
torch_dtype='auto'
|
| 31 |
+
).eval()
|
| 32 |
+
|
| 33 |
+
# Prompt content: "hi"
|
| 34 |
+
messages = [
|
| 35 |
+
{"role": "user", "content": "hi"}
|
| 36 |
+
]
|
| 37 |
+
|
| 38 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
| 39 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
| 40 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
| 41 |
+
|
| 42 |
+
# Model response: "Hello! How can I assist you today?"
|
| 43 |
+
print(response)
|
| 44 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
checkpoint-735/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
base_model: microsoft/phi-2
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset 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. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
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).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.10.0
|
checkpoint-735/adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "microsoft/phi-2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"fc1",
|
| 24 |
+
"dense",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"fc2",
|
| 28 |
+
"q_proj"
|
| 29 |
+
],
|
| 30 |
+
"task_type": "CAUSAL_LM",
|
| 31 |
+
"use_dora": false,
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
checkpoint-735/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e0ecee99d3d1fc5d0eca14df6922f840bc932f64e85e487835f7f2f89889f29
|
| 3 |
+
size 1124667084
|
checkpoint-735/added_tokens.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"\t\t": 50294,
|
| 3 |
+
"\t\t\t": 50293,
|
| 4 |
+
"\t\t\t\t": 50292,
|
| 5 |
+
"\t\t\t\t\t": 50291,
|
| 6 |
+
"\t\t\t\t\t\t": 50290,
|
| 7 |
+
"\t\t\t\t\t\t\t": 50289,
|
| 8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
| 9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
| 10 |
+
" ": 50286,
|
| 11 |
+
" ": 50285,
|
| 12 |
+
" ": 50284,
|
| 13 |
+
" ": 50283,
|
| 14 |
+
" ": 50282,
|
| 15 |
+
" ": 50281,
|
| 16 |
+
" ": 50280,
|
| 17 |
+
" ": 50279,
|
| 18 |
+
" ": 50278,
|
| 19 |
+
" ": 50277,
|
| 20 |
+
" ": 50276,
|
| 21 |
+
" ": 50275,
|
| 22 |
+
" ": 50274,
|
| 23 |
+
" ": 50273,
|
| 24 |
+
" ": 50272,
|
| 25 |
+
" ": 50271,
|
| 26 |
+
" ": 50270,
|
| 27 |
+
" ": 50269,
|
| 28 |
+
" ": 50268,
|
| 29 |
+
" ": 50267,
|
| 30 |
+
" ": 50266,
|
| 31 |
+
" ": 50265,
|
| 32 |
+
" ": 50264,
|
| 33 |
+
" ": 50263,
|
| 34 |
+
" ": 50262,
|
| 35 |
+
" ": 50261,
|
| 36 |
+
" ": 50260,
|
| 37 |
+
" ": 50259,
|
| 38 |
+
" ": 50258,
|
| 39 |
+
" ": 50257
|
| 40 |
+
}
|
checkpoint-735/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-735/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ae76fefef7ff36525f1251cffef5afe6b6d5d6ff5e2caa60fdad02427b0498
|
| 3 |
+
size 189066386
|
checkpoint-735/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
| 3 |
+
size 888
|
checkpoint-735/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93c2c09161904af0293b3aba7d511441de69bb10ec5a0620be8d3661daa010d5
|
| 3 |
+
size 14244
|
checkpoint-735/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:295f3c4338d56d308cd765625a3f9c4d16085ee98c53626e247e229e0ca87ab2
|
| 3 |
+
size 1064
|
checkpoint-735/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-735/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-735/tokenizer_config.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 319 |
+
"clean_up_tokenization_spaces": true,
|
| 320 |
+
"eos_token": "<|endoftext|>",
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"pad_token": "<|endoftext|>",
|
| 323 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 324 |
+
"unk_token": "<|endoftext|>"
|
| 325 |
+
}
|
checkpoint-735/trainer_state.json
ADDED
|
@@ -0,0 +1,224 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.996941896024465,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 735,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 0.2513757646083832,
|
| 14 |
+
"learning_rate": 1.0135135135135135e-05,
|
| 15 |
+
"loss": 1.5178,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 0.38634929060935974,
|
| 21 |
+
"learning_rate": 2.027027027027027e-05,
|
| 22 |
+
"loss": 1.4603,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.31,
|
| 27 |
+
"grad_norm": 0.5580678582191467,
|
| 28 |
+
"learning_rate": 2.995461422087746e-05,
|
| 29 |
+
"loss": 1.3665,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.41,
|
| 34 |
+
"grad_norm": 0.6025068163871765,
|
| 35 |
+
"learning_rate": 2.881996974281392e-05,
|
| 36 |
+
"loss": 1.2772,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.51,
|
| 41 |
+
"grad_norm": 0.6379350423812866,
|
| 42 |
+
"learning_rate": 2.768532526475038e-05,
|
| 43 |
+
"loss": 1.2555,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.61,
|
| 48 |
+
"grad_norm": 0.666475236415863,
|
| 49 |
+
"learning_rate": 2.655068078668684e-05,
|
| 50 |
+
"loss": 1.2434,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.71,
|
| 55 |
+
"grad_norm": 0.7137765288352966,
|
| 56 |
+
"learning_rate": 2.54160363086233e-05,
|
| 57 |
+
"loss": 1.2304,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.82,
|
| 62 |
+
"grad_norm": 0.6858211159706116,
|
| 63 |
+
"learning_rate": 2.428139183055976e-05,
|
| 64 |
+
"loss": 1.1842,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.92,
|
| 69 |
+
"grad_norm": 0.6926656365394592,
|
| 70 |
+
"learning_rate": 2.314674735249622e-05,
|
| 71 |
+
"loss": 1.1929,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.02,
|
| 76 |
+
"grad_norm": 0.6960567235946655,
|
| 77 |
+
"learning_rate": 2.2012102874432675e-05,
|
| 78 |
+
"loss": 1.1852,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.12,
|
| 83 |
+
"grad_norm": 0.6939908266067505,
|
| 84 |
+
"learning_rate": 2.087745839636914e-05,
|
| 85 |
+
"loss": 1.17,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.22,
|
| 90 |
+
"grad_norm": 0.7124253511428833,
|
| 91 |
+
"learning_rate": 1.97428139183056e-05,
|
| 92 |
+
"loss": 1.1512,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.33,
|
| 97 |
+
"grad_norm": 0.6936700344085693,
|
| 98 |
+
"learning_rate": 1.8608169440242055e-05,
|
| 99 |
+
"loss": 1.1686,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.43,
|
| 104 |
+
"grad_norm": 0.7236443758010864,
|
| 105 |
+
"learning_rate": 1.747352496217852e-05,
|
| 106 |
+
"loss": 1.1702,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.53,
|
| 111 |
+
"grad_norm": 0.7483662366867065,
|
| 112 |
+
"learning_rate": 1.6338880484114978e-05,
|
| 113 |
+
"loss": 1.1655,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.63,
|
| 118 |
+
"grad_norm": 0.8027617931365967,
|
| 119 |
+
"learning_rate": 1.5204236006051437e-05,
|
| 120 |
+
"loss": 1.1616,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.73,
|
| 125 |
+
"grad_norm": 0.8072408437728882,
|
| 126 |
+
"learning_rate": 1.4069591527987896e-05,
|
| 127 |
+
"loss": 1.1828,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.83,
|
| 132 |
+
"grad_norm": 0.7527270913124084,
|
| 133 |
+
"learning_rate": 1.2934947049924356e-05,
|
| 134 |
+
"loss": 1.1429,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.94,
|
| 139 |
+
"grad_norm": 0.7795941829681396,
|
| 140 |
+
"learning_rate": 1.1800302571860818e-05,
|
| 141 |
+
"loss": 1.1738,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.04,
|
| 146 |
+
"grad_norm": 0.8151872158050537,
|
| 147 |
+
"learning_rate": 1.0665658093797276e-05,
|
| 148 |
+
"loss": 1.1376,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.14,
|
| 153 |
+
"grad_norm": 0.7859562635421753,
|
| 154 |
+
"learning_rate": 9.531013615733736e-06,
|
| 155 |
+
"loss": 1.1459,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.24,
|
| 160 |
+
"grad_norm": 0.8044187426567078,
|
| 161 |
+
"learning_rate": 8.396369137670198e-06,
|
| 162 |
+
"loss": 1.1523,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.34,
|
| 167 |
+
"grad_norm": 0.8209382891654968,
|
| 168 |
+
"learning_rate": 7.261724659606657e-06,
|
| 169 |
+
"loss": 1.1165,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.45,
|
| 174 |
+
"grad_norm": 0.8191347122192383,
|
| 175 |
+
"learning_rate": 6.127080181543117e-06,
|
| 176 |
+
"loss": 1.1574,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.55,
|
| 181 |
+
"grad_norm": 0.864337682723999,
|
| 182 |
+
"learning_rate": 4.992435703479576e-06,
|
| 183 |
+
"loss": 1.1237,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.65,
|
| 188 |
+
"grad_norm": 0.8072352409362793,
|
| 189 |
+
"learning_rate": 3.857791225416037e-06,
|
| 190 |
+
"loss": 1.1432,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.75,
|
| 195 |
+
"grad_norm": 0.8192684054374695,
|
| 196 |
+
"learning_rate": 2.7231467473524962e-06,
|
| 197 |
+
"loss": 1.1176,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.85,
|
| 202 |
+
"grad_norm": 0.7951787710189819,
|
| 203 |
+
"learning_rate": 1.5885022692889562e-06,
|
| 204 |
+
"loss": 1.1419,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.96,
|
| 209 |
+
"grad_norm": 0.8341733813285828,
|
| 210 |
+
"learning_rate": 4.5385779122541606e-07,
|
| 211 |
+
"loss": 1.1387,
|
| 212 |
+
"step": 725
|
| 213 |
+
}
|
| 214 |
+
],
|
| 215 |
+
"logging_steps": 25,
|
| 216 |
+
"max_steps": 735,
|
| 217 |
+
"num_input_tokens_seen": 0,
|
| 218 |
+
"num_train_epochs": 3,
|
| 219 |
+
"save_steps": 500,
|
| 220 |
+
"total_flos": 4.82271317563392e+16,
|
| 221 |
+
"train_batch_size": 1,
|
| 222 |
+
"trial_name": null,
|
| 223 |
+
"trial_params": null
|
| 224 |
+
}
|
checkpoint-735/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2b8e2df042fde9c2da60ff10cdc7a124d0d8ccc76398ef52ab7c06cec47179a
|
| 3 |
+
size 4984
|
checkpoint-735/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
|
| 9 |
+
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
|
| 10 |
+
},
|
| 11 |
+
"bos_token_id": 50256,
|
| 12 |
+
"embd_pdrop": 0.0,
|
| 13 |
+
"eos_token_id": 50256,
|
| 14 |
+
"hidden_act": "gelu_new",
|
| 15 |
+
"hidden_size": 2560,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 10240,
|
| 18 |
+
"layer_norm_eps": 1e-05,
|
| 19 |
+
"max_position_embeddings": 2048,
|
| 20 |
+
"model_type": "phi",
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_hidden_layers": 32,
|
| 23 |
+
"num_key_value_heads": 32,
|
| 24 |
+
"partial_rotary_factor": 0.4,
|
| 25 |
+
"qk_layernorm": false,
|
| 26 |
+
"resid_pdrop": 0.1,
|
| 27 |
+
"rope_scaling": null,
|
| 28 |
+
"rope_theta": 10000.0,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"torch_dtype": "float16",
|
| 31 |
+
"transformers_version": "4.39.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 50295
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.39.0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85c6c899093ae0bdb0ead8aa8b74916a32000a4931e17d05b024c8518b6d1686
|
| 3 |
+
size 4990950824
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0facb653ee8a9bdc7f2aa8a326b9428a878fb72f65357d9a112fad4f7099f841
|
| 3 |
+
size 559197566
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 5550098670
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.bias": "model-00002-of-00002.safetensors",
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 10 |
+
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 118 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 122 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 130 |
+
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 131 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 132 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 134 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 135 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 136 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
+
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 138 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 139 |
+
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 154 |
+
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 155 |
+
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 156 |
+
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 157 |
+
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 158 |
+
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 159 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 160 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 162 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 164 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 166 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 168 |
+
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 170 |
+
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 172 |
+
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 174 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 176 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 178 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 180 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 182 |
+
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 184 |
+
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 186 |
+
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 188 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 190 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 192 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 194 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 196 |
+
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 198 |
+
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 200 |
+
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 202 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 204 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 206 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 208 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 210 |
+
"model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 212 |
+
"model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 214 |
+
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 216 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 218 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 220 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 222 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 224 |
+
"model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 226 |
+
"model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 227 |
+
"model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 228 |
+
"model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 229 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 230 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 231 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 232 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 233 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 234 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 235 |
+
"model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 236 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 238 |
+
"model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 316 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 317 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 318 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 319 |
+
"model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 320 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 322 |
+
"model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 323 |
+
"model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 324 |
+
"model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 325 |
+
"model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 326 |
+
"model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 327 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 328 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 329 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 330 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 331 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 332 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 334 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 335 |
+
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 336 |
+
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 337 |
+
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 338 |
+
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 339 |
+
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 348 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 349 |
+
"model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 350 |
+
"model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 351 |
+
"model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 352 |
+
"model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 353 |
+
"model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
| 354 |
+
"model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
| 355 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 356 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 357 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 360 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 361 |
+
"model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
| 362 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 363 |
+
"model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
| 364 |
+
"model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
| 365 |
+
"model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
| 366 |
+
"model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
| 367 |
+
"model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
| 368 |
+
"model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
| 369 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 370 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 371 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 372 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 373 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 374 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 375 |
+
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
| 459 |
+
}
|
| 460 |
+
}
|
runs/Mar22_16-13-59_r-ambrosfitz-autotrain2-tunwm0pq-81bca-4nl3c/events.out.tfevents.1711124043.r-ambrosfitz-autotrain2-tunwm0pq-81bca-4nl3c.53.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4411676024cf7a4c8d9b093b073cb3d339bb7ffa45432bfcc1eca3d5847067bf
|
| 3 |
+
size 11811
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": " ",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": false
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": " ",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50259": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50260": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50261": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50262": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50263": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50264": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50265": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50266": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50267": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50268": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50269": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50270": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50271": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50272": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50273": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50274": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50275": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50276": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50277": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50278": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50279": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50280": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"50281": {
|
| 205 |
+
"content": " ",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": true,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
},
|
| 212 |
+
"50282": {
|
| 213 |
+
"content": " ",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": true,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": false
|
| 219 |
+
},
|
| 220 |
+
"50283": {
|
| 221 |
+
"content": " ",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": true,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": false
|
| 227 |
+
},
|
| 228 |
+
"50284": {
|
| 229 |
+
"content": " ",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": true,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": false
|
| 235 |
+
},
|
| 236 |
+
"50285": {
|
| 237 |
+
"content": " ",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": true,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": false
|
| 243 |
+
},
|
| 244 |
+
"50286": {
|
| 245 |
+
"content": " ",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": true,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": false
|
| 251 |
+
},
|
| 252 |
+
"50287": {
|
| 253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": true,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": false
|
| 259 |
+
},
|
| 260 |
+
"50288": {
|
| 261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": true,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": false
|
| 267 |
+
},
|
| 268 |
+
"50289": {
|
| 269 |
+
"content": "\t\t\t\t\t\t\t",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": true,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": false
|
| 275 |
+
},
|
| 276 |
+
"50290": {
|
| 277 |
+
"content": "\t\t\t\t\t\t",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": true,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": false
|
| 283 |
+
},
|
| 284 |
+
"50291": {
|
| 285 |
+
"content": "\t\t\t\t\t",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": true,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": false
|
| 291 |
+
},
|
| 292 |
+
"50292": {
|
| 293 |
+
"content": "\t\t\t\t",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": true,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": false
|
| 299 |
+
},
|
| 300 |
+
"50293": {
|
| 301 |
+
"content": "\t\t\t",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": true,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": false
|
| 307 |
+
},
|
| 308 |
+
"50294": {
|
| 309 |
+
"content": "\t\t",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": true,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": false
|
| 315 |
+
}
|
| 316 |
+
},
|
| 317 |
+
"bos_token": "<|endoftext|>",
|
| 318 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 319 |
+
"clean_up_tokenization_spaces": true,
|
| 320 |
+
"eos_token": "<|endoftext|>",
|
| 321 |
+
"model_max_length": 2048,
|
| 322 |
+
"pad_token": "<|endoftext|>",
|
| 323 |
+
"tokenizer_class": "CodeGenTokenizer",
|
| 324 |
+
"unk_token": "<|endoftext|>"
|
| 325 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2b8e2df042fde9c2da60ff10cdc7a124d0d8ccc76398ef52ab7c06cec47179a
|
| 3 |
+
size 4984
|
training_params.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": "microsoft/phi-2",
|
| 3 |
+
"project_name": "sabre-2B",
|
| 4 |
+
"data_path": "ambrosfitz/ps_data_v2.2",
|
| 5 |
+
"train_split": "train",
|
| 6 |
+
"valid_split": null,
|
| 7 |
+
"add_eos_token": true,
|
| 8 |
+
"block_size": 1024,
|
| 9 |
+
"model_max_length": 2048,
|
| 10 |
+
"padding": "right",
|
| 11 |
+
"trainer": "sft",
|
| 12 |
+
"use_flash_attention_2": false,
|
| 13 |
+
"log": "tensorboard",
|
| 14 |
+
"disable_gradient_checkpointing": false,
|
| 15 |
+
"logging_steps": -1,
|
| 16 |
+
"evaluation_strategy": "epoch",
|
| 17 |
+
"save_total_limit": 1,
|
| 18 |
+
"save_strategy": "epoch",
|
| 19 |
+
"auto_find_batch_size": false,
|
| 20 |
+
"mixed_precision": "fp16",
|
| 21 |
+
"lr": 3e-05,
|
| 22 |
+
"epochs": 3,
|
| 23 |
+
"batch_size": 1,
|
| 24 |
+
"warmup_ratio": 0.1,
|
| 25 |
+
"gradient_accumulation": 4,
|
| 26 |
+
"optimizer": "adamw_torch",
|
| 27 |
+
"scheduler": "linear",
|
| 28 |
+
"weight_decay": 0.0,
|
| 29 |
+
"max_grad_norm": 1.0,
|
| 30 |
+
"seed": 42,
|
| 31 |
+
"chat_template": "none",
|
| 32 |
+
"quantization": "int4",
|
| 33 |
+
"target_modules": "all-linear",
|
| 34 |
+
"merge_adapter": true,
|
| 35 |
+
"peft": true,
|
| 36 |
+
"lora_r": 16,
|
| 37 |
+
"lora_alpha": 32,
|
| 38 |
+
"lora_dropout": 0.05,
|
| 39 |
+
"model_ref": null,
|
| 40 |
+
"dpo_beta": 0.1,
|
| 41 |
+
"prompt_text_column": "prompt",
|
| 42 |
+
"text_column": "text",
|
| 43 |
+
"rejected_text_column": "rejected_text",
|
| 44 |
+
"push_to_hub": true,
|
| 45 |
+
"repo_id": "080-ai/sabre-2B",
|
| 46 |
+
"username": "080-ai"
|
| 47 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|