at676 commited on
Commit
1f4cca1
·
verified ·
1 Parent(s): b5873f8

Upload folder using huggingface_hub (#1)

Browse files

- 8e13c5ded1e3e7e6b7a8a910ac8c7b9b45455ca990113103446cee7e1b2fc85f (d0cfb0118477a1cfb03c58f849ea1df2421cd635)
- 6dbd3798945702ba59146bb4deab5b6154a022b6cfa8da646fbd3565d33f9228 (19252d2b77d8f7a41901b4a627356463a0d0e64b)
- 4a7d44bb2f901c73312ff62c974660ec2c065daba8bc39966a0b709ee76c48be (661fbfa7df6c7ed5e55ccd88300f3fafc8bce60a)
- b7503fba9a54e577d0c709255632251fc998e35dff2a530b3b318044e263ca7c (1cac042cbab1d6190c34d09a81dd0b585e3a616b)
- 6f42b2b400735d8d309d3db50358e78c1bdfc4f8b0927f40a1998fad528da994 (ec118b622bbaa6994d4df12ae9f64a74451296aa)

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
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "quip_params": {
22
+ "K": 2,
23
+ "L": 16,
24
+ "V": 2,
25
+ "codebook": "bitshift",
26
+ "codebook_version": 0,
27
+ "decode_mode": "quantlut_sym",
28
+ "td_x": 16,
29
+ "td_y": 16,
30
+ "tlut_bits": 9
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": "4.44.2",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "sdpa",
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 4096,
7
+ "pad_token_id": 0,
8
+ "temperature": 0.6,
9
+ "top_p": 0.9,
10
+ "transformers_version": "4.44.2"
11
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e8663f8050cc687de5bf58eb67e1f12b7277290a63ef5adcec58eb6000ac62
3
+ size 4965486872
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7440ab503c16a5a4c4e7a18fda6d5159697e1e0b49d861177cb8b38e0300923b
3
+ size 4987305552
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d74fb4fe8310b8965d9913f9410e8d8644eff0e2c63c6546c5f419d5cc75ce
3
+ size 4966419048
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474fc8942dcb8ae25d4bbf33b9a926d0022940d59cfea8fb062369a319a65e21
3
+ size 3272052240
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff