at676 commited on
Commit
bd499ad
1 Parent(s): b15210f

Upload folder using huggingface_hub (#1)

Browse files

- be2d6cc956301a61550b00ae4333333f391b79fe70bee92323b02740324f86ad (6ff743d232cdc24e7054f29184bc02af601c7c17)
- d03d170f712c88a83129315d4d48cb8871e4b2e49e0c9a947105de9aebf36a8e (ca73e07b0910180a1d41f453b2658c842a28321e)

Files changed (3) hide show
  1. config.json +40 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "relaxml/Llama-1-13b-hf",
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": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pretraining_tp": 1,
19
+ "quip_params": {
20
+ "codebook": "E8P12RVQ3B",
21
+ "codebook_version": 0,
22
+ "codesz": 8,
23
+ "fused": true,
24
+ "idx_dtype": "torch.int64",
25
+ "lora_rank": 0,
26
+ "model_version": 1,
27
+ "outlier_channel_split": false,
28
+ "packsz": 2.6666666666666665,
29
+ "rescale_WH": false,
30
+ "resid_scale_override": -1
31
+ },
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.34.0",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
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.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3ca54fff1cfd334cf5a7872f13dd42c998d0025c0f2d5b7170b589550272bb
3
+ size 5420806056