at676 commited on
Commit
0a1a5be
1 Parent(s): e48e7d1

Upload folder using huggingface_hub (#1)

Browse files

- a3613cf982231b7bdd0f90c5305d68e8d61b084611fe46a16962940964c93d44 (c68d0a11510a0087393c14dc21aecce56c72bd14)
- 779a9ccb8e2ffd008e886660784e4890cee56f425ae8ffc138722ee1f731e949 (86ec753df26bf831f7bb2297fb1b19b7003416c0)
- 5dd5186f9244a6c3b9d62ec3899df64586a6ec79a67db0d17d633294f6db0ba7 (a8c6dc30ace535938d2b30b861e36e1f4ac7a4d6)
- 890049bcfeccc7a9110f62f4f443f3bb98a9cc64d0807e80c98e7ff7ebc2686b (50a7c1774e3c2483d686e5a8ec9928d98e454226)
- 25cef6cf1998c3c93d510e8ff82f058af20af6de275352bfa3c3195eb394c299 (4fe73188712b8de350713832f006bbd74673146f)

config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-70b-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": "HI4B1C",
21
+ "codesz": 1,
22
+ "fused": true,
23
+ "idx_dtype": "torch.int32",
24
+ "lora_rank": 0,
25
+ "outlier_channel_split": false,
26
+ "packsz": 8,
27
+ "rescale_WH": false
28
+ },
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_scaling": null,
31
+ "rope_theta": 10000.0,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.34.0",
35
+ "use_cache": true,
36
+ "vocab_size": 32000
37
+ }
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-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9b479b6074694e2c375d1ad4be7e19f35f34a019f74bf8e13e4fe0830af033b
3
+ size 9985114318
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adc3ad247d9c63bdc6bf6c9c10f61877dc553996812cd84e8bdda0e74c6a391a
3
+ size 9880563026
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a372a22aad42e9c9a6d4926842bb77ee932052d30f782473a066e81682119f
3
+ size 9846974978
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6301f3f988a6d8fa0d2d7d2664ea9db17cc00674b83e45a9b4a7c78f56ef615c
3
+ size 5586287798
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff