Minami-su commited on
Commit
fd6295f
1 Parent(s): 3010e32

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Yi-34B-Chat/",
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": 7168,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 56,
16
+ "num_hidden_layers": 60,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "quip_params": {
20
+ "codebook": "E8P12",
21
+ "codesz": 8,
22
+ "fused": true,
23
+ "idx_dtype": "torch.int16",
24
+ "lora_rank": 0,
25
+ "outlier_channel_split": false,
26
+ "packsz": 1,
27
+ "rescale_WH": false
28
+ },
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_scaling": null,
31
+ "rope_theta": 5000000.0,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.34.0",
35
+ "use_cache": true,
36
+ "vocab_size": 64000
37
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 6,
3
+ "do_sample": true,
4
+ "eos_token_id": 7,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.8,
9
+ "transformers_version": "4.34.0"
10
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06113df2fbfa44b52a0438e8100ad17317f4d9d88dc63cc5bca1f11e17192ea5
3
+ size 9299840312
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219344ad24bf1dce79c486670ff685e91bd39c2fb388a1aa84eceab4cc71c8af
3
+ size 917504128
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff