at676 commited on
Commit
4600ca6
1 Parent(s): fac53ac

Upload folder using huggingface_hub (#1)

Browse files

- 2d23b3e8712146d07a575e6edde6941e6b0abaa1e5242e7b7f97a540744bc99c (4ecdb7ccbc20ccafe418e4cb189755844914572d)
- 5024fda3dd26bde975dadae3dd965bdd2dd79cdae2d90c13dad8d5a1773374b5 (444bda9a62b581a3edf46f4d014fe09e3cb35e4a)
- 4d177b721728f8d7b006626584ea6a730174b8b11f2bfb353d1eb4900556120c (6f475649cd1e12abf6e1d0d43fa5e36a8d1914e7)
- 6135c4ea7c3232747ee01c99414dfb4ae3af8b7b4e57dae61b18a20838cf982c (08cee58441045d241f854c694160875e8eb9e309)

config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-70b-chat-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": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
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-05,
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 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.34.0"
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298fe14bea903f78948e865c082fac02d0e649a58bfd941845c221cfd3ceab23
3
+ size 9895032772
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47859dcdffa8b8e5a7c97a400f97313b82561017bc21a510a7099f4adea34a43
3
+ size 9956399254
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee0b50b2f5ee142955056ee4cae32b93bf25ad41c0c32e7fb3394230b44d8820
3
+ size 6891093958
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff