jc3464 commited on
Commit
8f798e6
1 Parent(s): 1dc4784

Upload folder using huggingface_hub (#1)

Browse files

- 388e364c095ec7f44483358505abdebfef04e6d1ffc293dc854aace92cc2e880 (28f0e24e3547c48814606d62221c301d358b5883)
- 3b46752d769c86808208bd7079a8c00f90a47341f1298686c9c310d99ecac471 (451d153c77906c4b023dcbfefb0d0fff99f341c3)
- 17e9449facd6c804cb848952d35b20e065deffc0fd134493542a1c1f78a1a1e5 (e96f3bc3de8ac08fd71925a6410a5085f34c1ac8)

config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/work/desa_data/meta_llama1/huggingface_65B/",
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": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 22016,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 64,
18
+ "pretraining_tp": 1,
19
+ "quip_params": {
20
+ "codebook": "E8P12",
21
+ "codesz": 8,
22
+ "idx_dtype": "torch.int16",
23
+ "lora_rank": 0,
24
+ "outlier_channel_split": false,
25
+ "rescale_WH": false
26
+ },
27
+ "rms_norm_eps": 1e-05,
28
+ "rope_scaling": null,
29
+ "rope_theta": 10000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float16",
32
+ "transformers_version": "4.34.0",
33
+ "use_cache": true,
34
+ "vocab_size": 32000
35
+ }
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": "4.34.0"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db8853ccde71bee061b39de760b774fddbfd13bbd594f01c6d5c4044654cc7f1
3
+ size 9914510142
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52004edfcc80d3331eacbd9ffa2dfb5b31dd44a47fb578d59cde1b4977898389
3
+ size 7348018442
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff