Commit
•
463beb5
1
Parent(s):
5df3f18
Upload folder using huggingface_hub
Browse files- .gitattributes +14 -0
- compiled/002e47ecb433d86b46c1.neff +3 -0
- compiled/27b9ae2747e681472f0f.neff +3 -0
- compiled/347ecd13e9a213b3c6a3.neff +3 -0
- compiled/64de654e0a6a8a80a36b.neff +3 -0
- compiled/6d25eb142954e695ea56.neff +3 -0
- compiled/82e01244d3f6ba0ce352.neff +3 -0
- compiled/8fe9a7a8f8fc6a776493.neff +3 -0
- compiled/9dfc3aef573e69e28c6a.neff +3 -0
- compiled/b2b22c0802c289f93ee9.neff +3 -0
- compiled/be7b02fb092f8eb4557b.neff +3 -0
- compiled/c9fd176cc710e975296d.neff +3 -0
- compiled/d43a5de0ce956dc53000.neff +3 -0
- compiled/d85f08804b747035c4fe.neff +3 -0
- compiled/de4141881c11ee945be9.neff +3 -0
- config.json +41 -0
- generation_config.json +6 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
.gitattributes
CHANGED
@@ -33,3 +33,17 @@ 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/002e47ecb433d86b46c1.neff filter=lfs diff=lfs merge=lfs -text
|
37 |
+
compiled/27b9ae2747e681472f0f.neff filter=lfs diff=lfs merge=lfs -text
|
38 |
+
compiled/347ecd13e9a213b3c6a3.neff filter=lfs diff=lfs merge=lfs -text
|
39 |
+
compiled/64de654e0a6a8a80a36b.neff filter=lfs diff=lfs merge=lfs -text
|
40 |
+
compiled/6d25eb142954e695ea56.neff filter=lfs diff=lfs merge=lfs -text
|
41 |
+
compiled/82e01244d3f6ba0ce352.neff filter=lfs diff=lfs merge=lfs -text
|
42 |
+
compiled/8fe9a7a8f8fc6a776493.neff filter=lfs diff=lfs merge=lfs -text
|
43 |
+
compiled/9dfc3aef573e69e28c6a.neff filter=lfs diff=lfs merge=lfs -text
|
44 |
+
compiled/b2b22c0802c289f93ee9.neff filter=lfs diff=lfs merge=lfs -text
|
45 |
+
compiled/be7b02fb092f8eb4557b.neff filter=lfs diff=lfs merge=lfs -text
|
46 |
+
compiled/c9fd176cc710e975296d.neff filter=lfs diff=lfs merge=lfs -text
|
47 |
+
compiled/d43a5de0ce956dc53000.neff filter=lfs diff=lfs merge=lfs -text
|
48 |
+
compiled/d85f08804b747035c4fe.neff filter=lfs diff=lfs merge=lfs -text
|
49 |
+
compiled/de4141881c11ee945be9.neff filter=lfs diff=lfs merge=lfs -text
|
compiled/002e47ecb433d86b46c1.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e7c747bd04636dc02f3c5d713cbf57527522dbadd2cfb19dcad886811824e9f
|
3 |
+
size 12002304
|
compiled/27b9ae2747e681472f0f.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e4206db8e137d53a96f9832765738247b4c7f9cf8fa72d20cf2428238dab628
|
3 |
+
size 12770304
|
compiled/347ecd13e9a213b3c6a3.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc05f0d6d60e433a902ad1627f7c8f26b5eb7986a56cb51bdad7f1c3ecd45ffe
|
3 |
+
size 12053504
|
compiled/64de654e0a6a8a80a36b.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e6a1489b7f41a519c5f2ac5e20b348421295fbc73eae9abb3ecc557eeea2b44
|
3 |
+
size 15596544
|
compiled/6d25eb142954e695ea56.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f4f5391e0e164c5f36ad2965e276ddecc9d695235a506ffd9964bfea9824e2
|
3 |
+
size 3533824
|
compiled/82e01244d3f6ba0ce352.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc66dcfec3e6a60119b30ede48ac77407c264d728e05041ce618773fcda3b989
|
3 |
+
size 12954624
|
compiled/8fe9a7a8f8fc6a776493.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72ff88590d39a0881828684a8e95030fbc07dc51f872373d4017997c70af3f2f
|
3 |
+
size 12934144
|
compiled/9dfc3aef573e69e28c6a.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b4ad5b6b914f715bb313e815424eea8f66af30e4ef38bbe33dd935fbceee12d
|
3 |
+
size 6226944
|
compiled/b2b22c0802c289f93ee9.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d1e8ff75492509970d1f9e0f68be7c152f5c49008772067d4564fde0b5c4a71
|
3 |
+
size 13722624
|
compiled/be7b02fb092f8eb4557b.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aeb147b6ecd478092c29dda1e564acfd75fc8858a973148afa56901b09f5c9d
|
3 |
+
size 13323264
|
compiled/c9fd176cc710e975296d.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afc65d4dfdc301d3101795d170ee59768347ae9e956cd3b7195d5879790b8880
|
3 |
+
size 13138944
|
compiled/d43a5de0ce956dc53000.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e4af7c0bf867abc8902255bd4c8baf0e077abe0a0d10031a2d64fc1d88121da
|
3 |
+
size 12913664
|
compiled/d85f08804b747035c4fe.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24644998da87b35e26d3744e0d6d808b6c441d7b330eddd9272d919ef8a30e71
|
3 |
+
size 13005824
|
compiled/de4141881c11ee945be9.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe728edd32976894577bab516eedeebcc0643a57390e156a42fc451f0e5e7f71
|
3 |
+
size 15125504
|
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": "bf16",
|
17 |
+
"batch_size": 1,
|
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": 8192,
|
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": null,
|
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 |
+
}
|
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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": null,
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|