davidshtian commited on
Commit
3be9509
1 Parent(s): f0a1c54

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/2597130f0fc80197d922.neff filter=lfs diff=lfs merge=lfs -text
37
+ compiled/2bd35d714e3733a974fc.neff filter=lfs diff=lfs merge=lfs -text
compiled/2597130f0fc80197d922.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05f8dbad5d1149bcc7f2f8994a4b56353057270517939c383d8d315d0657e99
3
+ size 2089984
compiled/2bd35d714e3733a974fc.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b017a066a3249e2be75465e8feffc53a433411bfcc74667644b57aa2a1006d89
3
+ size 7834624
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
3
+ "architectures": [
4
+ "MistralForCausalLM"
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": "mistral",
15
+ "neuron": {
16
+ "auto_cast_type": "bf16",
17
+ "batch_size": 4,
18
+ "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.2",
19
+ "checkpoint_revision": "41b61a33a2483885c981aa79e0df6b32407ed873",
20
+ "compiler_type": "neuronx-cc",
21
+ "compiler_version": "2.13.66.0+6dfecc895",
22
+ "num_cores": 24,
23
+ "sequence_length": 2048,
24
+ "task": "text-generation"
25
+ },
26
+ "num_attention_heads": 32,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 8,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.36.2",
35
+ "use_cache": true,
36
+ "vocab_size": 32000
37
+ }
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
+ }