jc3464 commited on
Commit
e2204a6
1 Parent(s): 1cfae3e

Upload folder using huggingface_hub (#1)

Browse files

- 8c5260e38aede5219f71c0dc9320f7901de0b0371509ffe777622fb5c3761de6 (cfa989a87339379663b66107498e5bdd1927e293)
- f4a55aa1f2125e2df23fb85b5701996584c37ffed57df8a6b965899e2e6ff1c8 (2b9179f91e6d81304ccfdab124054a4be1c35268)
- ade22b161b41e62f62b9d326a0acf84ccda5a22c29a133577bfd010cbc9ba62e (d529f93bfd3ffe47507c6da38fa09989aad75d38)
- 07ff3d7799f80153b1d60b0794c3daa52cec90ed0056ab6b9eeecc78fa48f4ac (05c808edaef06341f3868aa30b618839a8693356)
- 0fa3c4f3138a6d232627f001179bab78aa8453837d1c10a509171ab5fe32cbb6 (33a23e2649e396ef15d85488ea9e7f044e4442c7)

config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "relaxml/Llama-1-65b-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": 22016,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 64,
18
+ "pretraining_tp": 1,
19
+ "quip_params": {
20
+ "codebook": "HI2B1C",
21
+ "codebook_version": 0,
22
+ "codesz": 1,
23
+ "fused": true,
24
+ "idx_dtype": "torch.int32",
25
+ "lora_rank": 0,
26
+ "model_version": 1,
27
+ "outlier_channel_split": false,
28
+ "packsz": 8,
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 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44694b1903be2c7648cd02bb8406ef678de10a848571be1caeb5ad8aa901deb9
3
+ size 9974730576
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23876a710d6b5c1110906f18eae95bd9c975bb4c8f45660ee49c51fc1d244de1
3
+ size 9991906048
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2944ba37f24685f5c593b82049572ce6d03c725fa348b758e0547b13e31fa72
3
+ size 9855491642
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb9f1e4413c631cd32ca88ee2b92576d96cc7f599a8a63997d33e5a718ff0f2
3
+ size 3630378758
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff