at676 commited on
Commit
cc2ffbb
·
1 Parent(s): fe0ad3b

Upload folder using huggingface_hub (#1)

Browse files

- 5159c22d30b6c1d36d4a9240bf9a5e52fed9054c87e90fc5ad8b87791533d160 (eb5a4372710b73b0b9b9eea75cd4acbcdf2270d1)
- b0a1a5e802994c8034299d199d82e272f244865c2d51f53de7f56fee7015e783 (c411780056d78cfdaf783c5c8d28a16ddaff9f55)
- 1b74505eb3c9130c7d17e15da86b7e8c93833f3643f1051508f2e6c6cc91e09a (a643f6985652d80b0efbaf3d9e90149e20d1e487)
- 663dc152e6ad28ba9936ef1f9b0506d67232b8ffc21ebcce8f6c10c757d69051 (cc9ce724c2c234f596912935c589303841163cd8)
- 11ae611e65a57b7142a44f88a3c2965e1ab3b0022f0678ed307cf321a0eef0b0 (7081569b0f3c35f7500f3df28c1bfdd172f42f4f)

config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "E8P12RVQ4B",
21
+ "codebook_version": 1,
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,
29
+ "rescale_WH": false,
30
+ "resid_scale_override": 3.6
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-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a547e65025cd7b03df160589c419d8d1b38d9877f467ea7c449d407b84c6f7ab
3
+ size 9985104748
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba80817e9d0f12a81e619c7ad12cb3992c035137f3bcb9b844994b5e8e0a7c59
3
+ size 9880552968
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5e75148f1df3b611aaa017049edf48f043c217b8845fb2bca5f1d793d993b96
3
+ size 9846965214
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f13300fa6555216a87910529c31b95ac57ee6917f09b922b6a2b506ab342489
3
+ size 5586283278
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff