atsuki-yamaguchi
commited on
Commit
•
63eb15d
1
Parent(s):
fcfa1ea
Upload folder using huggingface_hub
Browse files- README.md +15 -29
- adapter_config.json +1 -29
- config.json +2 -2
- model-00001-of-00006.safetensors +2 -2
- model-00002-of-00006.safetensors +2 -2
- model-00003-of-00006.safetensors +2 -2
- model-00004-of-00006.safetensors +2 -2
- model-00005-of-00006.safetensors +2 -2
- model-00006-of-00006.safetensors +2 -2
- model.safetensors.index.json +28 -28
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +4 -28
- tokenizer.json +0 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,35 +1,21 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
language:
|
4 |
-
- ja
|
5 |
---
|
6 |
-
|
7 |
-
===
|
8 |
|
9 |
-
## How to use
|
10 |
-
```python
|
11 |
-
from peft import AutoPeftModelForCausalLM
|
12 |
-
from transformers import AutoTokenizer
|
13 |
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
|
|
|
|
|
|
|
|
|
|
21 |
|
22 |
-
## Citation
|
23 |
-
```
|
24 |
-
@article{yamaguchi2024empirical,
|
25 |
-
title={An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative {LLM} Inference},
|
26 |
-
author={Atsuki Yamaguchi and Aline Villavicencio and Nikolaos Aletras},
|
27 |
-
journal={ArXiv},
|
28 |
-
year={2024},
|
29 |
-
volume={abs/2402.10712},
|
30 |
-
url={https://arxiv.org/abs/2402.10712}
|
31 |
-
}
|
32 |
-
```
|
33 |
|
34 |
-
|
35 |
-
For more details, please visit https://github.com/gucci-j/llm-cva
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
|
|
|
|
3 |
---
|
4 |
+
## Training procedure
|
|
|
5 |
|
|
|
|
|
|
|
|
|
6 |
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: True
|
10 |
+
- load_in_4bit: False
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: fp4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float32
|
18 |
+
### Framework versions
|
19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
+
- PEFT 0.5.0
|
|
adapter_config.json
CHANGED
@@ -1,29 +1 @@
|
|
1 |
-
{
|
2 |
-
"auto_mapping": null,
|
3 |
-
"base_model_name_or_path": "atsuki-yamaguchi/Mistral-7B-v0.1-clpp-ja",
|
4 |
-
"bias": "none",
|
5 |
-
"fan_in_fan_out": false,
|
6 |
-
"inference_mode": true,
|
7 |
-
"init_lora_weights": true,
|
8 |
-
"layers_pattern": null,
|
9 |
-
"layers_to_transform": null,
|
10 |
-
"lora_alpha": 32,
|
11 |
-
"lora_dropout": 0.05,
|
12 |
-
"modules_to_save": [
|
13 |
-
"lm_head",
|
14 |
-
"embed_tokens"
|
15 |
-
],
|
16 |
-
"peft_type": "LORA",
|
17 |
-
"r": 8,
|
18 |
-
"revision": null,
|
19 |
-
"target_modules": [
|
20 |
-
"q_proj",
|
21 |
-
"v_proj",
|
22 |
-
"k_proj",
|
23 |
-
"o_proj",
|
24 |
-
"gate_proj",
|
25 |
-
"down_proj",
|
26 |
-
"up_proj"
|
27 |
-
],
|
28 |
-
"task_type": "CAUSAL_LM"
|
29 |
-
}
|
|
|
1 |
+
{"auto_mapping": null, "base_model_name_or_path": "atsuki-yamaguchi/Mistral-7B-v0.1-clpp-ja", "bias": "none", "fan_in_fan_out": false, "inference_mode": true, "init_lora_weights": true, "layers_pattern": null, "layers_to_transform": null, "lora_alpha": 32, "lora_dropout": 0.05, "modules_to_save": ["lm_head", "embed_tokens"], "peft_type": "LORA", "r": 8, "revision": null, "target_modules": ["q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "task_type": "CAUSAL_LM"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
@@ -18,7 +18,7 @@
|
|
18 |
"rope_theta": 10000.0,
|
19 |
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
-
"torch_dtype": "
|
22 |
"transformers_version": "4.35.0.dev0",
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 32000
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
18 |
"rope_theta": 10000.0,
|
19 |
"sliding_window": 4096,
|
20 |
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "float64",
|
22 |
"transformers_version": "4.35.0.dev0",
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 32000
|
model-00001-of-00006.safetensors
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:d6deef5ea687d29e730b7861e369102168c3929aa1174631bc4c9ec8ad5095fd
|
3 |
+
size 4941026032
|
model-00002-of-00006.safetensors
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 sha256:9d32f4e850f6bda3b1aa1fd85a372377274b9a8a166dab9047fd4cd958199746
|
3 |
+
size 4999813072
|
model-00003-of-00006.safetensors
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 sha256:8f3b1794261ba1e27810d553cd2b5f949fcc3a6fe37ba9b09f5033bc7e5de472
|
3 |
+
size 4832007496
|
model-00004-of-00006.safetensors
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:f72da02290a5f95304a8cff4c7216f30405a3f0072ac1b2b1a906e9748ff10a7
|
3 |
+
size 4999813120
|
model-00005-of-00006.safetensors
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:f289adb9a536fe1aed9ba102e26c6b07185a467cb77def237d8715d378831662
|
3 |
+
size 4999813128
|
model-00006-of-00006.safetensors
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:be962dec7dca8150b39d0a05b00e8181a30446d8510bbdd1fb5b96b8d4017cd4
|
3 |
+
size 4718777176
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00006-of-00006.safetensors",
|
@@ -25,8 +25,8 @@
|
|
25 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
26 |
"model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
27 |
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
28 |
-
"model.layers.10.mlp.gate_proj.weight": "model-
|
29 |
-
"model.layers.10.mlp.up_proj.weight": "model-
|
30 |
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
31 |
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
32 |
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
@@ -68,24 +68,24 @@
|
|
68 |
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
69 |
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
70 |
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
71 |
-
"model.layers.15.input_layernorm.weight": "model-
|
72 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
73 |
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
74 |
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
75 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
76 |
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
77 |
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
78 |
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
79 |
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
80 |
"model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
81 |
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
82 |
-
"model.layers.16.mlp.gate_proj.weight": "model-
|
83 |
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
84 |
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
85 |
-
"model.layers.16.self_attn.k_proj.weight": "model-
|
86 |
-
"model.layers.16.self_attn.o_proj.weight": "model-
|
87 |
-
"model.layers.16.self_attn.q_proj.weight": "model-
|
88 |
-
"model.layers.16.self_attn.v_proj.weight": "model-
|
89 |
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
90 |
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
91 |
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
@@ -131,11 +131,11 @@
|
|
131 |
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
132 |
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
133 |
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
134 |
-
"model.layers.21.input_layernorm.weight": "model-
|
135 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
136 |
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
137 |
-
"model.layers.21.mlp.up_proj.weight": "model-
|
138 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
139 |
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
140 |
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
141 |
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
@@ -145,10 +145,10 @@
|
|
145 |
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
146 |
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
147 |
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
148 |
-
"model.layers.22.self_attn.k_proj.weight": "model-
|
149 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
150 |
-
"model.layers.22.self_attn.q_proj.weight": "model-
|
151 |
-
"model.layers.22.self_attn.v_proj.weight": "model-
|
152 |
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
153 |
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
154 |
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
@@ -187,8 +187,8 @@
|
|
187 |
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
188 |
"model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
189 |
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
190 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
191 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
192 |
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
193 |
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
194 |
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
@@ -239,11 +239,11 @@
|
|
239 |
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
240 |
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
241 |
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
242 |
-
"model.layers.4.input_layernorm.weight": "model-
|
243 |
-
"model.layers.4.mlp.down_proj.weight": "model-
|
244 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
245 |
-
"model.layers.4.mlp.up_proj.weight": "model-
|
246 |
-
"model.layers.4.post_attention_layernorm.weight": "model-
|
247 |
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
248 |
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
249 |
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
@@ -253,10 +253,10 @@
|
|
253 |
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
254 |
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
255 |
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
256 |
-
"model.layers.5.self_attn.k_proj.weight": "model-
|
257 |
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
258 |
-
"model.layers.5.self_attn.q_proj.weight": "model-
|
259 |
-
"model.layers.5.self_attn.v_proj.weight": "model-
|
260 |
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
261 |
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
262 |
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 29491216384
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"lm_head.weight": "model-00006-of-00006.safetensors",
|
|
|
25 |
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
26 |
"model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
27 |
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
30 |
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
31 |
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
32 |
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
|
|
68 |
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
69 |
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
70 |
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
73 |
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
74 |
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
76 |
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
77 |
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
78 |
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
79 |
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
80 |
"model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
81 |
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
83 |
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
84 |
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
89 |
"model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
90 |
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
91 |
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
|
|
131 |
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
132 |
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
133 |
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
136 |
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
139 |
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
140 |
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
141 |
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
|
|
145 |
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
146 |
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
147 |
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
152 |
"model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
153 |
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
154 |
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
|
|
187 |
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
188 |
"model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
189 |
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
192 |
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
193 |
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
194 |
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
|
|
239 |
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
240 |
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
241 |
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
244 |
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
247 |
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
248 |
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
249 |
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
|
|
253 |
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
254 |
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
255 |
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
257 |
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
260 |
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
261 |
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
262 |
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bf9cc3eb296729d77de6918b554460f2e0b5386fda248f222c235e779193b55
|
3 |
+
size 567855324
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f21655ba8bdde9d44ecb6be12e1fe5543c4cdb67e0e5a746b9dcacce9091f703
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:394f63e155c1870e1adf89d6e808adbedc007a65149566630f394b538ee37fe7
|
3 |
+
size 1064
|
special_tokens_map.json
CHANGED
@@ -1,18 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "[CLS]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"eos_token": {
|
17 |
"content": "</s>",
|
18 |
"lstrip": false,
|
@@ -20,13 +8,7 @@
|
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
-
"mask_token":
|
24 |
-
"content": "[MASK]",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
"pad_token": {
|
31 |
"content": "[PAD]",
|
32 |
"lstrip": false,
|
@@ -34,13 +16,7 @@
|
|
34 |
"rstrip": false,
|
35 |
"single_word": false
|
36 |
},
|
37 |
-
"sep_token":
|
38 |
-
"content": "[SEP]",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
"unk_token": {
|
45 |
"content": "[UNK]",
|
46 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "[CLS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"eos_token": {
|
5 |
"content": "</s>",
|
6 |
"lstrip": false,
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
11 |
+
"mask_token": "[MASK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"pad_token": {
|
13 |
"content": "[PAD]",
|
14 |
"lstrip": false,
|
|
|
16 |
"rstrip": false,
|
17 |
"single_word": false
|
18 |
},
|
19 |
+
"sep_token": "[SEP]",
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"unk_token": {
|
21 |
"content": "[UNK]",
|
22 |
"lstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68ca55416176e6a638fb88f1e1e385f0b51da4a42d9ff8b55573866968fc2805
|
3 |
+
size 4664
|