Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +23 -0
- adapter_model.bin +3 -0
- checkpoint-61500/README.md +238 -0
- checkpoint-61500/adapter_config.json +23 -0
- checkpoint-61500/adapter_model.bin +3 -0
- checkpoint-61500/optimizer.pt +3 -0
- checkpoint-61500/rng_state.pth +3 -0
- checkpoint-61500/scheduler.pt +3 -0
- checkpoint-61500/special_tokens_map.json +24 -0
- checkpoint-61500/tokenizer.json +0 -0
- checkpoint-61500/tokenizer.model +3 -0
- checkpoint-61500/tokenizer_config.json +37 -0
- checkpoint-61500/trainer_state.json +313 -0
- checkpoint-61500/training_args.bin +3 -0
- config.json +28 -0
- generation_config.json +7 -0
- ko-llama2-finetune/training_params.json +44 -0
- main.py +51 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +298 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +37 -0
- training_args.bin +3 -0
- training_params.json +1 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation
|
5 |
+
widget:
|
6 |
+
- text: "I love AutoTrain because "
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Trained Using AutoTrain
|
adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f14f10e8ebcd363b8b970010a440e16af86b78b24f9d246d7400dd9bb75db0c8
|
3 |
+
size 33600461
|
checkpoint-61500/README.md
ADDED
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
base_model: TinyPixel/Llama-2-7B-bf16-sharded
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Shared by [optional]:** [More Information Needed]
|
22 |
+
- **Model type:** [More Information Needed]
|
23 |
+
- **Language(s) (NLP):** [More Information Needed]
|
24 |
+
- **License:** [More Information Needed]
|
25 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
26 |
+
|
27 |
+
### Model Sources [optional]
|
28 |
+
|
29 |
+
<!-- Provide the basic links for the model. -->
|
30 |
+
|
31 |
+
- **Repository:** [More Information Needed]
|
32 |
+
- **Paper [optional]:** [More Information Needed]
|
33 |
+
- **Demo [optional]:** [More Information Needed]
|
34 |
+
|
35 |
+
## Uses
|
36 |
+
|
37 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
38 |
+
|
39 |
+
### Direct Use
|
40 |
+
|
41 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
42 |
+
|
43 |
+
[More Information Needed]
|
44 |
+
|
45 |
+
### Downstream Use [optional]
|
46 |
+
|
47 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
## Bias, Risks, and Limitations
|
58 |
+
|
59 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
### Recommendations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
66 |
+
|
67 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
68 |
+
|
69 |
+
## How to Get Started with the Model
|
70 |
+
|
71 |
+
Use the code below to get started with the model.
|
72 |
+
|
73 |
+
[More Information Needed]
|
74 |
+
|
75 |
+
## Training Details
|
76 |
+
|
77 |
+
### Training Data
|
78 |
+
|
79 |
+
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
80 |
+
|
81 |
+
[More Information Needed]
|
82 |
+
|
83 |
+
### Training Procedure
|
84 |
+
|
85 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
86 |
+
|
87 |
+
#### Preprocessing [optional]
|
88 |
+
|
89 |
+
[More Information Needed]
|
90 |
+
|
91 |
+
|
92 |
+
#### Training Hyperparameters
|
93 |
+
|
94 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
95 |
+
|
96 |
+
#### Speeds, Sizes, Times [optional]
|
97 |
+
|
98 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
99 |
+
|
100 |
+
[More Information Needed]
|
101 |
+
|
102 |
+
## Evaluation
|
103 |
+
|
104 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
105 |
+
|
106 |
+
### Testing Data, Factors & Metrics
|
107 |
+
|
108 |
+
#### Testing Data
|
109 |
+
|
110 |
+
<!-- This should link to a Data Card if possible. -->
|
111 |
+
|
112 |
+
[More Information Needed]
|
113 |
+
|
114 |
+
#### Factors
|
115 |
+
|
116 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Metrics
|
121 |
+
|
122 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
### Results
|
127 |
+
|
128 |
+
[More Information Needed]
|
129 |
+
|
130 |
+
#### Summary
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
## Model Examination [optional]
|
135 |
+
|
136 |
+
<!-- Relevant interpretability work for the model goes here -->
|
137 |
+
|
138 |
+
[More Information Needed]
|
139 |
+
|
140 |
+
## Environmental Impact
|
141 |
+
|
142 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
143 |
+
|
144 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
145 |
+
|
146 |
+
- **Hardware Type:** [More Information Needed]
|
147 |
+
- **Hours used:** [More Information Needed]
|
148 |
+
- **Cloud Provider:** [More Information Needed]
|
149 |
+
- **Compute Region:** [More Information Needed]
|
150 |
+
- **Carbon Emitted:** [More Information Needed]
|
151 |
+
|
152 |
+
## Technical Specifications [optional]
|
153 |
+
|
154 |
+
### Model Architecture and Objective
|
155 |
+
|
156 |
+
[More Information Needed]
|
157 |
+
|
158 |
+
### Compute Infrastructure
|
159 |
+
|
160 |
+
[More Information Needed]
|
161 |
+
|
162 |
+
#### Hardware
|
163 |
+
|
164 |
+
[More Information Needed]
|
165 |
+
|
166 |
+
#### Software
|
167 |
+
|
168 |
+
[More Information Needed]
|
169 |
+
|
170 |
+
## Citation [optional]
|
171 |
+
|
172 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
173 |
+
|
174 |
+
**BibTeX:**
|
175 |
+
|
176 |
+
[More Information Needed]
|
177 |
+
|
178 |
+
**APA:**
|
179 |
+
|
180 |
+
[More Information Needed]
|
181 |
+
|
182 |
+
## Glossary [optional]
|
183 |
+
|
184 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## More Information [optional]
|
189 |
+
|
190 |
+
[More Information Needed]
|
191 |
+
|
192 |
+
## Model Card Authors [optional]
|
193 |
+
|
194 |
+
[More Information Needed]
|
195 |
+
|
196 |
+
## Model Card Contact
|
197 |
+
|
198 |
+
[More Information Needed]
|
199 |
+
|
200 |
+
|
201 |
+
## Training procedure
|
202 |
+
|
203 |
+
|
204 |
+
The following `bitsandbytes` quantization config was used during training:
|
205 |
+
- quant_method: bitsandbytes
|
206 |
+
- load_in_8bit: False
|
207 |
+
- load_in_4bit: True
|
208 |
+
- llm_int8_threshold: 6.0
|
209 |
+
- llm_int8_skip_modules: None
|
210 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
211 |
+
- llm_int8_has_fp16_weight: False
|
212 |
+
- bnb_4bit_quant_type: nf4
|
213 |
+
- bnb_4bit_use_double_quant: False
|
214 |
+
- bnb_4bit_compute_dtype: float16
|
215 |
+
|
216 |
+
### Framework versions
|
217 |
+
|
218 |
+
|
219 |
+
- PEFT 0.6.0.dev0
|
220 |
+
## Training procedure
|
221 |
+
|
222 |
+
|
223 |
+
The following `bitsandbytes` quantization config was used during training:
|
224 |
+
- quant_method: bitsandbytes
|
225 |
+
- load_in_8bit: False
|
226 |
+
- load_in_4bit: True
|
227 |
+
- llm_int8_threshold: 6.0
|
228 |
+
- llm_int8_skip_modules: None
|
229 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
230 |
+
- llm_int8_has_fp16_weight: False
|
231 |
+
- bnb_4bit_quant_type: nf4
|
232 |
+
- bnb_4bit_use_double_quant: False
|
233 |
+
- bnb_4bit_compute_dtype: float16
|
234 |
+
|
235 |
+
### Framework versions
|
236 |
+
|
237 |
+
|
238 |
+
- PEFT 0.6.0.dev0
|
checkpoint-61500/adapter_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
+
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
23 |
+
}
|
checkpoint-61500/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f14f10e8ebcd363b8b970010a440e16af86b78b24f9d246d7400dd9bb75db0c8
|
3 |
+
size 33600461
|
checkpoint-61500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:571eaeeeab8bbb90701a2d815295db938e0a181093710cac10c684c2902e4e16
|
3 |
+
size 67216581
|
checkpoint-61500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38e18ded1e13fe24e1aa46fb4e80c18154f259226d3821dab742802b888705e7
|
3 |
+
size 14575
|
checkpoint-61500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23faea91e69d4c48ae095221e5e09c44aefb534d984c5ddac9fb7e3355e9b42d
|
3 |
+
size 627
|
checkpoint-61500/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-61500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-61500/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-61500/tokenizer_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"bos_token": "<s>",
|
29 |
+
"clean_up_tokenization_spaces": false,
|
30 |
+
"eos_token": "</s>",
|
31 |
+
"model_max_length": 2048,
|
32 |
+
"pad_token": "</s>",
|
33 |
+
"sp_model_kwargs": {},
|
34 |
+
"tokenizer_class": "LlamaTokenizer",
|
35 |
+
"unk_token": "<unk>",
|
36 |
+
"use_default_system_prompt": true
|
37 |
+
}
|
checkpoint-61500/trainer_state.json
ADDED
@@ -0,0 +1,313 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 49.19829114944382,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 61500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 7.996130904401096e-06,
|
14 |
+
"loss": 0.9136,
|
15 |
+
"step": 1240
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 1.5992261808802192e-05,
|
20 |
+
"loss": 0.6938,
|
21 |
+
"step": 2480
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 2.398839271320329e-05,
|
26 |
+
"loss": 0.6666,
|
27 |
+
"step": 3720
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.01,
|
31 |
+
"learning_rate": 3.1984523617604385e-05,
|
32 |
+
"loss": 0.6509,
|
33 |
+
"step": 4960
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.01,
|
37 |
+
"learning_rate": 3.998065452200548e-05,
|
38 |
+
"loss": 0.6398,
|
39 |
+
"step": 6200
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.01,
|
43 |
+
"learning_rate": 4.797678542640658e-05,
|
44 |
+
"loss": 0.6298,
|
45 |
+
"step": 7440
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 7.01,
|
49 |
+
"learning_rate": 5.596646783814283e-05,
|
50 |
+
"loss": 0.6204,
|
51 |
+
"step": 8680
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 8.01,
|
55 |
+
"learning_rate": 6.396259874254393e-05,
|
56 |
+
"loss": 0.6104,
|
57 |
+
"step": 9920
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 9.01,
|
61 |
+
"learning_rate": 7.195228115428019e-05,
|
62 |
+
"loss": 0.601,
|
63 |
+
"step": 11160
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 10.02,
|
67 |
+
"learning_rate": 7.994841205868129e-05,
|
68 |
+
"loss": 0.5906,
|
69 |
+
"step": 12400
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 11.02,
|
73 |
+
"learning_rate": 8.79316459777527e-05,
|
74 |
+
"loss": 0.5796,
|
75 |
+
"step": 13640
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 12.02,
|
79 |
+
"learning_rate": 9.59277768821538e-05,
|
80 |
+
"loss": 0.5692,
|
81 |
+
"step": 14880
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 13.02,
|
85 |
+
"learning_rate": 0.0001039239077865549,
|
86 |
+
"loss": 0.5576,
|
87 |
+
"step": 16120
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 14.02,
|
91 |
+
"learning_rate": 0.000111920038690956,
|
92 |
+
"loss": 0.5452,
|
93 |
+
"step": 17360
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 15.02,
|
97 |
+
"learning_rate": 0.00011990972110269225,
|
98 |
+
"loss": 0.5337,
|
99 |
+
"step": 18600
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 16.03,
|
103 |
+
"learning_rate": 0.00012790585200709334,
|
104 |
+
"loss": 0.5209,
|
105 |
+
"step": 19840
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 17.03,
|
109 |
+
"learning_rate": 0.0001358955344188296,
|
110 |
+
"loss": 0.5085,
|
111 |
+
"step": 21080
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 18.03,
|
115 |
+
"learning_rate": 0.0001438916653232307,
|
116 |
+
"loss": 0.4964,
|
117 |
+
"step": 22320
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 19.03,
|
121 |
+
"learning_rate": 0.00015188134773496697,
|
122 |
+
"loss": 0.4832,
|
123 |
+
"step": 23560
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 20.03,
|
127 |
+
"learning_rate": 0.00015986458165403837,
|
128 |
+
"loss": 0.4706,
|
129 |
+
"step": 24800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 21.03,
|
133 |
+
"learning_rate": 0.00016786071255843948,
|
134 |
+
"loss": 0.4593,
|
135 |
+
"step": 26040
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 22.04,
|
139 |
+
"learning_rate": 0.00017585039497017573,
|
140 |
+
"loss": 0.4469,
|
141 |
+
"step": 27280
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 23.04,
|
145 |
+
"learning_rate": 0.00018384652587457684,
|
146 |
+
"loss": 0.4359,
|
147 |
+
"step": 28520
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 24.04,
|
151 |
+
"learning_rate": 0.00019183620828631308,
|
152 |
+
"loss": 0.4252,
|
153 |
+
"step": 29760
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 25.04,
|
157 |
+
"learning_rate": 0.0001998323391907142,
|
158 |
+
"loss": 0.4149,
|
159 |
+
"step": 31000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 26.04,
|
163 |
+
"learning_rate": 0.00019913088648861662,
|
164 |
+
"loss": 0.4045,
|
165 |
+
"step": 32240
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 27.04,
|
169 |
+
"learning_rate": 0.00019824242749923873,
|
170 |
+
"loss": 0.3923,
|
171 |
+
"step": 33480
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 28.05,
|
175 |
+
"learning_rate": 0.0001973546850090458,
|
176 |
+
"loss": 0.3812,
|
177 |
+
"step": 34720
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 29.05,
|
181 |
+
"learning_rate": 0.00019646622601966792,
|
182 |
+
"loss": 0.3703,
|
183 |
+
"step": 35960
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 30.05,
|
187 |
+
"learning_rate": 0.00019557776703029,
|
188 |
+
"loss": 0.3603,
|
189 |
+
"step": 37200
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 31.05,
|
193 |
+
"learning_rate": 0.0001946900245400971,
|
194 |
+
"loss": 0.3512,
|
195 |
+
"step": 38440
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 32.05,
|
199 |
+
"learning_rate": 0.00019380228204990418,
|
200 |
+
"loss": 0.342,
|
201 |
+
"step": 39680
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 33.05,
|
205 |
+
"learning_rate": 0.00019291382306052627,
|
206 |
+
"loss": 0.3336,
|
207 |
+
"step": 40920
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 34.05,
|
211 |
+
"learning_rate": 0.00019202536407114838,
|
212 |
+
"loss": 0.3261,
|
213 |
+
"step": 42160
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 35.06,
|
217 |
+
"learning_rate": 0.00019113833808014045,
|
218 |
+
"loss": 0.3187,
|
219 |
+
"step": 43400
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 36.06,
|
223 |
+
"learning_rate": 0.00019024987909076256,
|
224 |
+
"loss": 0.3118,
|
225 |
+
"step": 44640
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 37.06,
|
229 |
+
"learning_rate": 0.00018936142010138465,
|
230 |
+
"loss": 0.3052,
|
231 |
+
"step": 45880
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 38.06,
|
235 |
+
"learning_rate": 0.00018847367761119172,
|
236 |
+
"loss": 0.2991,
|
237 |
+
"step": 47120
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 39.06,
|
241 |
+
"learning_rate": 0.0001875852186218138,
|
242 |
+
"loss": 0.2933,
|
243 |
+
"step": 48360
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 40.06,
|
247 |
+
"learning_rate": 0.0001866974761316209,
|
248 |
+
"loss": 0.2878,
|
249 |
+
"step": 49600
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 41.07,
|
253 |
+
"learning_rate": 0.00018580901714224302,
|
254 |
+
"loss": 0.2824,
|
255 |
+
"step": 50840
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 42.07,
|
259 |
+
"learning_rate": 0.0001849212746520501,
|
260 |
+
"loss": 0.2778,
|
261 |
+
"step": 52080
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 43.07,
|
265 |
+
"learning_rate": 0.00018403353216185717,
|
266 |
+
"loss": 0.273,
|
267 |
+
"step": 53320
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 44.07,
|
271 |
+
"learning_rate": 0.00018314507317247926,
|
272 |
+
"loss": 0.2685,
|
273 |
+
"step": 54560
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 45.07,
|
277 |
+
"learning_rate": 0.00018225733068228636,
|
278 |
+
"loss": 0.2646,
|
279 |
+
"step": 55800
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 46.07,
|
283 |
+
"learning_rate": 0.00018136887169290845,
|
284 |
+
"loss": 0.2606,
|
285 |
+
"step": 57040
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 47.08,
|
289 |
+
"learning_rate": 0.00018048112920271552,
|
290 |
+
"loss": 0.2562,
|
291 |
+
"step": 58280
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 48.08,
|
295 |
+
"learning_rate": 0.00017959267021333764,
|
296 |
+
"loss": 0.2531,
|
297 |
+
"step": 59520
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 49.08,
|
301 |
+
"learning_rate": 0.00017870421122395975,
|
302 |
+
"loss": 0.2495,
|
303 |
+
"step": 60760
|
304 |
+
}
|
305 |
+
],
|
306 |
+
"logging_steps": 1240,
|
307 |
+
"max_steps": 310150,
|
308 |
+
"num_train_epochs": 50,
|
309 |
+
"save_steps": 500,
|
310 |
+
"total_flos": 1.9992255863036314e+19,
|
311 |
+
"trial_name": null,
|
312 |
+
"trial_params": null
|
313 |
+
}
|
checkpoint-61500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b29825818d2e1aa3fa34ca8842da982b43b7ca6f9af29e39c51c85d63e30053a
|
3 |
+
size 4091
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 11008,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 32,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.34.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.34.1"
|
7 |
+
}
|
ko-llama2-finetune/training_params.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "TinyPixel/Llama-2-7B-bf16-sharded",
|
3 |
+
"data_path": "royboy0416/ko-alpaca",
|
4 |
+
"project_name": "ko-llama2-finetune",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"text_column": "text",
|
8 |
+
"rejected_text_column": "rejected",
|
9 |
+
"token": null,
|
10 |
+
"lr": 0.0002,
|
11 |
+
"epochs": 10,
|
12 |
+
"batch_size": 8,
|
13 |
+
"warmup_ratio": 0.1,
|
14 |
+
"gradient_accumulation": 1,
|
15 |
+
"optimizer": "adamw_torch",
|
16 |
+
"scheduler": "linear",
|
17 |
+
"weight_decay": 0.0,
|
18 |
+
"max_grad_norm": 1.0,
|
19 |
+
"seed": 42,
|
20 |
+
"add_eos_token": false,
|
21 |
+
"block_size": -1,
|
22 |
+
"use_peft": true,
|
23 |
+
"lora_r": 16,
|
24 |
+
"lora_alpha": 32,
|
25 |
+
"lora_dropout": 0.05,
|
26 |
+
"logging_steps": -1,
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"save_total_limit": 1,
|
29 |
+
"save_strategy": "epoch",
|
30 |
+
"auto_find_batch_size": false,
|
31 |
+
"fp16": false,
|
32 |
+
"push_to_hub": false,
|
33 |
+
"use_int8": false,
|
34 |
+
"model_max_length": 2048,
|
35 |
+
"repo_id": null,
|
36 |
+
"use_int4": true,
|
37 |
+
"trainer": "sft",
|
38 |
+
"target_modules": null,
|
39 |
+
"merge_adapter": false,
|
40 |
+
"username": null,
|
41 |
+
"use_flash_attention_2": false,
|
42 |
+
"log": "none",
|
43 |
+
"disable_gradient_checkpointing": false
|
44 |
+
}
|
main.py
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import torch
|
2 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
3 |
+
from peft import PeftModel, PeftConfig
|
4 |
+
import argparse
|
5 |
+
|
6 |
+
model_id = "TinyPixel/Llama-2-7B-bf16-sharded"
|
7 |
+
peft_model_id = "checkpoint-3690"
|
8 |
+
|
9 |
+
config = PeftConfig.from_pretrained(peft_model_id)
|
10 |
+
|
11 |
+
bnb_config = BitsAndBytesConfig(
|
12 |
+
load_in_8bit=False,
|
13 |
+
load_in_4bit=True,
|
14 |
+
llm_int8_threshold=6.0,
|
15 |
+
llm_int8_skip_modules=None,
|
16 |
+
llm_int8_enable_fp32_cpu_offload=False,
|
17 |
+
llm_int8_has_fp16_weight=False,
|
18 |
+
bnb_4bit_quant_type="nf4",
|
19 |
+
bnb_4bit_use_double_quant=False,
|
20 |
+
bnb_4bit_compute_dtype="float16",
|
21 |
+
)
|
22 |
+
|
23 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"": 0})
|
24 |
+
model = PeftModel.from_pretrained(model, peft_model_id)
|
25 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
26 |
+
|
27 |
+
model.eval()
|
28 |
+
|
29 |
+
prompt = "Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction: %s ### Response: "
|
30 |
+
|
31 |
+
def gen(x):
|
32 |
+
q = prompt % (x,)
|
33 |
+
gened = model.generate(
|
34 |
+
**tokenizer(
|
35 |
+
q,
|
36 |
+
return_tensors='pt',
|
37 |
+
return_token_type_ids=False
|
38 |
+
).to('cuda'),
|
39 |
+
max_new_tokens=128,
|
40 |
+
early_stopping=True,
|
41 |
+
do_sample=True,
|
42 |
+
)
|
43 |
+
return tokenizer.decode(gened[0]).replace(q, "")
|
44 |
+
|
45 |
+
if __name__ == "__main__":
|
46 |
+
parser = argparse.ArgumentParser(description="Generate responses based on instructions.")
|
47 |
+
parser.add_argument("instruction", type=str, help="The instruction for generating a response.")
|
48 |
+
args = parser.parse_args()
|
49 |
+
|
50 |
+
response = gen(args.instruction)
|
51 |
+
print("Generated Response:", response)
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fff2fbcf96cfba877f3434afaa86899bff089d36ea6b58c2eb807e3536e0c6a0
|
3 |
+
size 9976620122
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6f07ded83cb72e550c48c361f7620e4488c32a2b33109ee3127377c1cce127c
|
3 |
+
size 3500310787
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476831232
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
296 |
+
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
297 |
+
}
|
298 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"bos_token": "<s>",
|
29 |
+
"clean_up_tokenization_spaces": false,
|
30 |
+
"eos_token": "</s>",
|
31 |
+
"model_max_length": 1000000000000000019884624838656,
|
32 |
+
"pad_token": null,
|
33 |
+
"sp_model_kwargs": {},
|
34 |
+
"tokenizer_class": "LlamaTokenizer",
|
35 |
+
"unk_token": "<unk>",
|
36 |
+
"use_default_system_prompt": true
|
37 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b29825818d2e1aa3fa34ca8842da982b43b7ca6f9af29e39c51c85d63e30053a
|
3 |
+
size 4091
|
training_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"model": "TinyPixel/Llama-2-7B-bf16-sharded", "data_path": "royboy0416/ko-alpaca", "project_name": "ko-llama2-finetune", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 50, "batch_size": 8, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 2048, "repo_id": "cepiloth/ko-llama2-finetune-ex4", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": true, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false}
|