Svak commited on
Commit
6c55080
·
verified ·
1 Parent(s): 89efb9d

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Sao10K/L3.1-70B-Hanami-x1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 8192,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 28672,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 64,
22
+ "num_hidden_layers": 80,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "quantization_config": {
26
+ "activation_scheme": "dynamic",
27
+ "ignored_layers": [
28
+ "lm_head"
29
+ ],
30
+ "quant_method": "fp8"
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": {
34
+ "factor": 8.0,
35
+ "high_freq_factor": 4.0,
36
+ "low_freq_factor": 1.0,
37
+ "original_max_position_embeddings": 8192,
38
+ "rope_type": "llama3"
39
+ },
40
+ "rope_theta": 500000.0,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.44.2",
44
+ "use_cache": true,
45
+ "vocab_size": 128256
46
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "transformers_version": "4.44.2"
10
+ }
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3661dba4b6e0c154bba545169b0c097275349a49bccdb9ff37653d9bad9af3d4
3
+ size 4819359900
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a507bc3aee992f98f0e47223786c654f6e70b847041cf6efddb0585ae89af3b0
3
+ size 4983039376
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a298565d37e5b41c47e70b142535f7a7ca68019c8cb297706edc3cfc224f6d2
3
+ size 4899121052
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507811585dd692ee6fa12fee4685cc104fa88dd85c3e70469f264327e7aa8979
3
+ size 4899154060
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff