at676 commited on
Commit
0b45a28
1 Parent(s): 3e95cb4

Upload folder using huggingface_hub (#1)

Browse files

- 57a460c7ef02ae8bfcd42dcdf060d335ab25612297601b7bc7cf78d7d0e92672 (24673e898b42b378993aa3588a99f3d3b0d04326)
- dcef94df04ad55601c0adfb5dc47ebdab0aa71a8d99909bfe069409055ba1bb1 (bd3f1a652db66be3f2b3ad9d8c5f3a058bffabe0)

Files changed (3) hide show
  1. config.json +40 -0
  2. generation_config.json +11 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
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
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pretraining_tp": 1,
21
+ "quip_params": {
22
+ "K": 4,
23
+ "L": 16,
24
+ "V": 2,
25
+ "codebook": "bitshift",
26
+ "codebook_version": 0,
27
+ "decode_mode": "quantlut_sym",
28
+ "td_x": 16,
29
+ "td_y": 16,
30
+ "tlut_bits": 9
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.44.2",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "sdpa",
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 4096,
7
+ "pad_token_id": 0,
8
+ "temperature": 0.6,
9
+ "top_p": 0.9,
10
+ "transformers_version": "4.44.2"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5de11ea7c0b3d0a8399f7655ae5c63ed8c9b3648cbd3b95ec5ad0922bb934d9
3
+ size 3768383152