Upload 17 files
Browse files- config.json +30 -0
- generation_config.json +6 -0
- model-00001-of-00059.safetensors +3 -0
- model-00002-of-00059.safetensors +3 -0
- model-00003-of-00059.safetensors +3 -0
- model-00004-of-00059.safetensors +3 -0
- model-00005-of-00059.safetensors +3 -0
- model-00006-of-00059.safetensors +3 -0
- model-00007-of-00059.safetensors +3 -0
- model-00008-of-00059.safetensors +3 -0
- model-00009-of-00059.safetensors +3 -0
- model-00010-of-00059.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MixtralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 6144,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 16384,
|
12 |
+
"max_position_embeddings": 65536,
|
13 |
+
"model_type": "mixtral",
|
14 |
+
"num_attention_heads": 48,
|
15 |
+
"num_experts_per_tok": 2,
|
16 |
+
"num_hidden_layers": 56,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"num_local_experts": 8,
|
19 |
+
"output_router_logits": false,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_theta": 1000000,
|
22 |
+
"router_aux_loss_coef": 0.001,
|
23 |
+
"router_jitter_noise": 0.0,
|
24 |
+
"sliding_window": null,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.40.0.dev0",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
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": "4.40.0.dev0"
|
6 |
+
}
|
model-00001-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768ee9473dc80d344a2e2646f5a31920185518bd88849bad8a1d007da445164a
|
3 |
+
size 4998663696
|
model-00002-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f002f7e9cf68697b27c8cf0a07db91e3ce6e6d59b9513dba2f2d66a6fee5667
|
3 |
+
size 4806799120
|
model-00003-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdbdfe1ed2b385a0350b92873abcbc02560ac03b878d3a5721755b0c78ce362f
|
3 |
+
size 4806799120
|
model-00004-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed1417d1e606a532b3259a451c9620996185224db310cb8dd656ee2fff30e6cd
|
3 |
+
size 4806799120
|
model-00005-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0495e05cd49186380188a44dfe8e26c681a0b7d16ddc8b2b13cf5de8aa6ef491
|
3 |
+
size 4806799120
|
model-00006-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ede4a77829087e9ded02253c6f9161296097911deccf04cc83fd15a74c3f325
|
3 |
+
size 4806799120
|
model-00007-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fca5eb95354127542dcbf685b34608aa90e1a21a0c3aaf1a4c263008085ca65
|
3 |
+
size 4806799120
|
model-00008-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f621867d4881def425ac71860e6d0ac848b5cd492106f6c243500f2c8ea2218
|
3 |
+
size 4806799120
|
model-00009-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da43fa4dc8af9949c76b759f4c4483467905d1cac0fbefd5df197e28a8055c7
|
3 |
+
size 4806799120
|
model-00010-of-00059.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77d0a1aba9dc68a5e8f5383d93c72261cd763dbbf1095a2f59a5017448b6a100
|
3 |
+
size 4806799120
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
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 |
+
}
|