sudhanshu746
commited on
Commit
•
6e098ba
1
Parent(s):
b65a599
Upload folder using huggingface_hub
Browse files- config.json +38 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -0
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/.cache/huggingface/hub/models--deepseek-ai--deepseek-math-7b-rl/snapshots/f3cd419a172ff5a100e9a563ebfe7900d78e9740",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 100000,
|
9 |
+
"eos_token_id": 100001,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"moe_intermediate_size": 11008,
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_hidden_layers": 30,
|
20 |
+
"num_key_value_heads": 32,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"quantization_config": {
|
23 |
+
"bits": 4,
|
24 |
+
"group_size": 128,
|
25 |
+
"modules_to_not_convert": null,
|
26 |
+
"quant_method": "awq",
|
27 |
+
"version": "gemm",
|
28 |
+
"zero_point": true
|
29 |
+
},
|
30 |
+
"rms_norm_eps": 1e-06,
|
31 |
+
"rope_scaling": null,
|
32 |
+
"rope_theta": 10000,
|
33 |
+
"tie_word_embeddings": false,
|
34 |
+
"torch_dtype": "float16",
|
35 |
+
"transformers_version": "4.41.0",
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 102400
|
38 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100000,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 100001,
|
6 |
+
"transformers_version": "4.41.0"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07a95779b72ac0e322fd0438610464d147a1d2fc601fed740e272ede6fccb7fd
|
3 |
+
size 4832506640
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"100000": {
|
6 |
+
"content": "<|begin▁of▁sentence|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"100001": {
|
14 |
+
"content": "<|end▁of▁sentence|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
23 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
|
24 |
+
"clean_up_tokenization_spaces": false,
|
25 |
+
"eos_token": "<|end▁of▁sentence|>",
|
26 |
+
"model_max_length": 4096,
|
27 |
+
"sp_model_kwargs": {},
|
28 |
+
"tokenizer_class": "LlamaTokenizer",
|
29 |
+
"unk_token": null,
|
30 |
+
"use_default_system_prompt": false
|
31 |
+
}
|