Upload folder using huggingface_hub
Browse files- config.json +53 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantize_config.json +13 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +13 -0
config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/Yi-9B-GPTQ-4bit-128g-actorder_False/",
|
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": 48,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"quantization_config": {
|
22 |
+
"batch_size": 1,
|
23 |
+
"bits": 4,
|
24 |
+
"block_name_to_quantize": null,
|
25 |
+
"cache_block_outputs": true,
|
26 |
+
"damp_percent": 0.01,
|
27 |
+
"dataset": null,
|
28 |
+
"desc_act": false,
|
29 |
+
"exllama_config": {
|
30 |
+
"version": 1
|
31 |
+
},
|
32 |
+
"group_size": 128,
|
33 |
+
"max_input_length": null,
|
34 |
+
"model_seqlen": null,
|
35 |
+
"module_name_preceding_first_block": null,
|
36 |
+
"modules_in_block_to_quantize": null,
|
37 |
+
"pad_token_id": null,
|
38 |
+
"quant_method": "gptq",
|
39 |
+
"sym": true,
|
40 |
+
"tokenizer": null,
|
41 |
+
"true_sequential": true,
|
42 |
+
"use_cuda_fp16": false,
|
43 |
+
"use_exllama": true
|
44 |
+
},
|
45 |
+
"rms_norm_eps": 1e-06,
|
46 |
+
"rope_scaling": null,
|
47 |
+
"rope_theta": 10000,
|
48 |
+
"tie_word_embeddings": false,
|
49 |
+
"torch_dtype": "float16",
|
50 |
+
"transformers_version": "4.38.2",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 64000
|
53 |
+
}
|
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": "4.38.2"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58b87ff7c97659329e4ccf4ca747167e308bf35270f0fce86bf45bbcb3b448b4
|
3 |
+
size 4850067192
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a364adcb4408ea19daa4c12f9279fe3fd882e6bf8be4821ac2e81c2ba717fcb5
|
3 |
+
size 524288128
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quantize_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"damp_percent": 0.01,
|
5 |
+
"desc_act": false,
|
6 |
+
"static_groups": false,
|
7 |
+
"sym": true,
|
8 |
+
"true_sequential": true,
|
9 |
+
"model_name_or_path": null,
|
10 |
+
"model_file_base_name": null,
|
11 |
+
"is_marlin_format": false,
|
12 |
+
"quant_method": "gptq"
|
13 |
+
}
|
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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"model_max_length": 4096,
|
5 |
+
"unk_token": "<unk>",
|
6 |
+
"bos_token": "<|startoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"pad_token": "<unk>",
|
9 |
+
"sp_model_kwargs": {},
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"legacy": true,
|
12 |
+
"tokenizer_class": "LlamaTokenizer"
|
13 |
+
}
|