stenio123 commited on
Commit
219d749
1 Parent(s): 8a3b578

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,11 @@ 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
+ Mixtral-8x7B-v0.1-neuron/2ea52780bf51a876a581.neff filter=lfs diff=lfs merge=lfs -text
37
+ Mixtral-8x7B-v0.1-neuron/3fe4f2529b098b312b3d.neff filter=lfs diff=lfs merge=lfs -text
38
+ Mixtral-8x7B-v0.1-neuron/725df4e18f3ab8c1c81b.neff filter=lfs diff=lfs merge=lfs -text
39
+ Mixtral-8x7B-v0.1-neuron/89b2c507c6636c4dea97.neff filter=lfs diff=lfs merge=lfs -text
40
+ Mixtral-8x7B-v0.1-neuron/a33d060e5a79aa33be42.neff filter=lfs diff=lfs merge=lfs -text
41
+ Mixtral-8x7B-v0.1-neuron/c8c632d274fd83ce4bbd.neff filter=lfs diff=lfs merge=lfs -text
42
+ Mixtral-8x7B-v0.1-neuron/cfda3dc8284fff50864d.neff filter=lfs diff=lfs merge=lfs -text
43
+ Mixtral-8x7B-v0.1-neuron/d6c11b23d8989af31d83.neff filter=lfs diff=lfs merge=lfs -text
Mixtral-8x7B-v0.1-neuron/2ea52780bf51a876a581.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131fa897d6be1b6c681473ec698e7c3b2ad1c1fe8b15ebbdeac0fedebfd15e0c
3
+ size 14818304
Mixtral-8x7B-v0.1-neuron/3fe4f2529b098b312b3d.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8b41292967035b34102a7b3d9ff4a26d1e244e3c3b1a86476c41314db65133
3
+ size 12934144
Mixtral-8x7B-v0.1-neuron/725df4e18f3ab8c1c81b.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a4764c9d5eac22f41f0db161d184743a8b628abf527daf6cbd972441c59b02
3
+ size 12964864
Mixtral-8x7B-v0.1-neuron/89b2c507c6636c4dea97.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2752897332341ca7179eb0d2de21e867f770d52e5a74a9530200f5775ba7144b
3
+ size 12739584
Mixtral-8x7B-v0.1-neuron/a33d060e5a79aa33be42.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b39184060c0eced82cd3faa1fc496d77daf8fcbd4eb8424f292562b5d36952c
3
+ size 15125504
Mixtral-8x7B-v0.1-neuron/c8c632d274fd83ce4bbd.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7517eb361f880f762ffbac8b4ffe5dd9749e12385d82b43b2db82956c435aa8
3
+ size 11971584
Mixtral-8x7B-v0.1-neuron/cfda3dc8284fff50864d.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff510ba3b3f43618e5cc82a636b79c6200cb6815be6f590909ab4002770a10b
3
+ size 13005824
Mixtral-8x7B-v0.1-neuron/d6c11b23d8989af31d83.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c05606d0af9006e2a367a24943918fb3a5edb9047904cac4b9e3cd4febd913
3
+ size 12913664
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mixtral-8x7B-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
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000.0,
23
+ "router_aux_loss_coef": 0.02,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.40.2",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }