kkondratenko commited on
Commit
ac06eda
1 Parent(s): 9fd6af5

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ compiled/9eb09a01e5ea9a5fd104.neff filter=lfs diff=lfs merge=lfs -text
37
+ compiled/cf2f858ecfbbd6964629.neff filter=lfs diff=lfs merge=lfs -text
compiled/9eb09a01e5ea9a5fd104.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b93c993f53fae0fac22c237a495a49aaf592df651ef7ee5925ffb3d1f633030b
3
+ size 6677504
compiled/cf2f858ecfbbd6964629.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19ef6a14427dd9db379eb22276c9060c1c50c972cac4767bb74a0e2d232cb64
3
+ size 12258304
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "neuron": {
16
+ "auto_cast_type": "fp16",
17
+ "batch_size": 4,
18
+ "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
19
+ "checkpoint_revision": "1e637f2d7cb0a9d6fb1922f305cb784995190a83",
20
+ "compiler_type": "neuronx-cc",
21
+ "compiler_version": "2.13.66.0+6dfecc895",
22
+ "num_cores": 8,
23
+ "sequence_length": 2048,
24
+ "task": "text-generation"
25
+ },
26
+ "num_attention_heads": 32,
27
+ "num_experts_per_tok": 2,
28
+ "num_hidden_layers": 32,
29
+ "num_key_value_heads": 8,
30
+ "num_local_experts": 8,
31
+ "output_router_logits": false,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_theta": 1000000.0,
34
+ "router_aux_loss_coef": 0.02,
35
+ "sliding_window": 4096,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.36.2",
39
+ "use_cache": true,
40
+ "vocab_size": 32000
41
+ }
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": "4.36.2"
6
+ }