First model version
Browse files- README.md +65 -3
- added_tokens.json +3 -0
- config.json +28 -0
- generation_config.json +6 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +298 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +51 -0
README.md
CHANGED
@@ -1,3 +1,65 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
### Model Sources
|
3 |
+
Paper: LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
|
4 |
+
|
5 |
+
Link: https://arxiv.org/pdf/2407
|
6 |
+
|
7 |
+
### Model Description
|
8 |
+
|
9 |
+
🔥 LLaMAX-7B-MetaMath is fully fine-tuned on the MetaMathQA dataset based on the powerful multilingual model LLaMAX-7B.
|
10 |
+
|
11 |
+
🔥 Compared with the [MetaMath-7B](https://huggingface.co/meta-math/MetaMath-7B-V1.0), LLaMAX-7B-MetaMath performs significantly better in mathematical reasoning in low-resource languages, improving the average accuracy of low-resource languages on MGSM dataset by up to 18.8%.
|
12 |
+
|
13 |
+
🔥 LLaMAX-7B-MetaMath demonstrates good multilingual math reasoning capability in all languages, improving the average accuracy by 6.2% across all languages in MGSM dataset.
|
14 |
+
|
15 |
+
### Model Usage
|
16 |
+
|
17 |
+
Prompt template:
|
18 |
+
```angular2html
|
19 |
+
def Prompt_template(query):
|
20 |
+
prompt = (
|
21 |
+
"Below is an instruction that describes a task. "
|
22 |
+
"Write a response that appropriately completes the request.\n\n"
|
23 |
+
f"### Instruction:\n{query}\n\n### Response: Let's think step by step."
|
24 |
+
)
|
25 |
+
return prompt
|
26 |
+
```
|
27 |
+
|
28 |
+
Code Example:
|
29 |
+
```angular2html
|
30 |
+
from transformers import AutoTokenizer, LlamaForCausalLM
|
31 |
+
|
32 |
+
model = LlamaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
|
33 |
+
tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
|
34 |
+
|
35 |
+
query = "Bert fills out the daily crossword puzzle in the newspaper every day. He uses a pencil to fill out the puzzles every two weeks. On average, it takes him 1050 words to use up a pencil. How many words are in each crossword puzzle on average?"
|
36 |
+
prompt = Prompt_template(query)
|
37 |
+
inputs = tokenizer(prompt, return_tensors="pt")
|
38 |
+
|
39 |
+
generate_ids = model.generate(inputs.input_ids, max_length=30)
|
40 |
+
tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
|
41 |
+
|
42 |
+
# => "If Bert uses up a pencil to fill out the puzzles every two weeks and it takes him 1050
|
43 |
+
words to use up a pencil, then he must be filling out 1050 words of crossword puzzles every
|
44 |
+
two weeks. To find out how many words are in each daily crossword puzzle, we need to divide
|
45 |
+
the total number of words (1050) by the number of days in two weeks (14). So, there are
|
46 |
+
1050/14 = 75 words in each daily crossword puzzle on average. #### The answer is: 75“
|
47 |
+
```
|
48 |
+
### Experiments
|
49 |
+
We evaluated LLaMAX-7B-MetaMath on the MGSM dataset. Compared with MetaMath-7B, LLaMAX-7B-MetaMath achieves a leading on both high-resource languages (Hrl.) and low-resource languages (Lrl.).
|
50 |
+
|
51 |
+
| MGSM | Bn | Th | Sw | Ja | Zh | De | Fr | Ru | Es | En | Lrl. | Hrl. | Avg. |
|
52 |
+
|-----------------------------|-------|------|----|-------|------|----|----|------|----|----|------|------|--------|
|
53 |
+
| MetaMath-7B (official) | 6.8 | 7.2 |6.8| 36.4 | 38.4 | 55.2|54.4| 52.0 |57.2|68.8| 6.9 | 51.8 | 38.32 |
|
54 |
+
| MetaMath-7B (Reproduced) | 6.0 | 10.0 |4.4|36.4|42.8|52.8|56.0|48.8|58.8|64.8| 6.8 | 51.5 | 38.08 |
|
55 |
+
| LLaMAX-7B-MetaMath |26.8| 24.0 |26.0|35.6|42.4|56.8|55.2|53.6|56.8|65.6| 25.6 | 52.3 | 44.28 |
|
56 |
+
|
57 |
+
### Citation
|
58 |
+
if our model helps your work, please cite this paper:
|
59 |
+
|
60 |
+
```
|
61 |
+
@inproceedings{Huang2024MindMergerEB,
|
62 |
+
title={XLLaMA2: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages},
|
63 |
+
year={2024},
|
64 |
+
}
|
65 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../LLMs/TransLlama/",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 32,
|
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": "float32",
|
25 |
+
"transformers_version": "4.38.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32001
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.38.2"
|
6 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c6b03fc583f9433e177e4dbda9a96301d59239555fb6695d233c35244a2fb38
|
3 |
+
size 4840412800
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d778284d7adc3880d4e3283f7324a7c81c57b2e03abf37a487fd08d1072f7ad2
|
3 |
+
size 4857206856
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:325d450fae9c488767cc9ab2ab4303ac8c413a70b0d0b36facb563ae1d8fe500
|
3 |
+
size 4857206904
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2445df4d16e6bc2d2f076710b868445bc40be805372d7d2fce11f85282bac93
|
3 |
+
size 4857206904
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e95f3160e5b488cc4d6e9a1d7e3b37c7e83a364e8a775f25ef626da45fb2d60d
|
3 |
+
size 4857206904
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:beba90370bb1089eddb2478a8fe985b7e28b52788eabfdecd0a1fc445f407e0d
|
3 |
+
size 2684488496
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26953695232
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-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-00002-of-00006.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-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",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-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-00003-of-00006.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00006.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-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",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_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-00004-of-00006.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-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-00004-of-00006.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-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",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-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",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_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-00005-of-00006.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-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",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00006-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-00001-of-00006.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-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-00001-of-00006.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-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",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-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-00001-of-00006.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-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",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
296 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
297 |
+
}
|
298 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"bos_token": "<s>",
|
40 |
+
"clean_up_tokenization_spaces": false,
|
41 |
+
"eos_token": "</s>",
|
42 |
+
"legacy": false,
|
43 |
+
"model_max_length": 512,
|
44 |
+
"pad_token": "[PAD]",
|
45 |
+
"padding_side": "right",
|
46 |
+
"sp_model_kwargs": {},
|
47 |
+
"spaces_between_special_tokens": false,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": false
|
51 |
+
}
|