model upload
Browse files- config.json +37 -0
- generation_config.json +6 -0
- model-00001-of-00029.safetensors +3 -0
- model-00002-of-00029.safetensors +3 -0
- model-00003-of-00029.safetensors +3 -0
- model-00004-of-00029.safetensors +3 -0
- model-00005-of-00029.safetensors +3 -0
- model-00006-of-00029.safetensors +3 -0
- model-00007-of-00029.safetensors +3 -0
- model-00008-of-00029.safetensors +3 -0
- model-00009-of-00029.safetensors +3 -0
- model-00010-of-00029.safetensors +3 -0
- model-00011-of-00029.safetensors +3 -0
- model-00012-of-00029.safetensors +3 -0
- model-00013-of-00029.safetensors +3 -0
- model-00014-of-00029.safetensors +3 -0
- model-00015-of-00029.safetensors +3 -0
- model-00016-of-00029.safetensors +3 -0
- model-00017-of-00029.safetensors +3 -0
- model-00018-of-00029.safetensors +3 -0
- model-00019-of-00029.safetensors +3 -0
- model-00020-of-00029.safetensors +3 -0
- model-00021-of-00029.safetensors +3 -0
- model-00022-of-00029.safetensors +3 -0
- model-00023-of-00029.safetensors +3 -0
- model-00024-of-00029.safetensors +3 -0
- model-00025-of-00029.safetensors +3 -0
- model-00026-of-00029.safetensors +3 -0
- model-00027-of-00029.safetensors +3 -0
- model-00028-of-00029.safetensors +3 -0
- model-00029-of-00029.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mixtral-8x22B-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": 6144,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 16384,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 48,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"quantization_config": {
|
22 |
+
"activation_scheme": "dynamic",
|
23 |
+
"ignored_layers": [
|
24 |
+
"lm_head"
|
25 |
+
],
|
26 |
+
"quant_method": "fp8"
|
27 |
+
},
|
28 |
+
"rms_norm_eps": 1e-05,
|
29 |
+
"rope_theta": 1000000,
|
30 |
+
"router_aux_loss_coef": 0.001,
|
31 |
+
"sliding_window": null,
|
32 |
+
"tie_word_embeddings": false,
|
33 |
+
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.38.1",
|
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": "4.38.1"
|
6 |
+
}
|
model-00001-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afc12cbea99edf873c159dc0bdecc5e0d525a4a71abec62508ad7b41c4adc699
|
3 |
+
size 4998698216
|
model-00002-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90f10c1469dfb33fcf5ee7ec89e6138d2d17b5ad59c73e2c305eacf202e908f7
|
3 |
+
size 4907497516
|
model-00003-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3052e1bef2dcdc30cfe8edade8c5796fc2d90f949f93d2a64b8576371d12a08d
|
3 |
+
size 4907497516
|
model-00004-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37b5b71812c8436f36d267ac373abbcc63e3076f04364f7a72bb88fd81ae97f8
|
3 |
+
size 4907497516
|
model-00005-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d3b66b905204399ed175996184302e97c4acd46b1614a962eca42d4d3e5647c
|
3 |
+
size 4907497516
|
model-00006-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:171b8a21d0dbfeef1a3bc5ba225e3735f227b40eda2718b2c638010345a32f09
|
3 |
+
size 4907497620
|
model-00007-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3a3075cdb044693055ab2a1fe50d42cca9630959d7a064454c3f66f4245f18f
|
3 |
+
size 4907497636
|
model-00008-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43ac2aa07176ce8639c547bc2fc6f1f42d1ad946a682b12d4c9db6f8d45dc0a7
|
3 |
+
size 4907497636
|
model-00009-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47ea9643714a7b1a0505070099bea10355567092b43266be093650f136192064
|
3 |
+
size 4907497636
|
model-00010-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bce62421f9f344ddec321d3dd582209b683840ee0af4725b8a78d53ac79c864b
|
3 |
+
size 4907497636
|
model-00011-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:060366d30097783bb6b5db27ac6e1fc4cef47dd2b32d353bc323f08e5cba034e
|
3 |
+
size 4907497636
|
model-00012-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05814e6e70d16731d893e394e6c11799fd50066dbaa510fe2216146db0d3a765
|
3 |
+
size 4907497636
|
model-00013-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d354312020c2f1e34e85606e4dc6a788376ccd646d1dfa5484b829670fe6a66d
|
3 |
+
size 4907497636
|
model-00014-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cad350e36ba4fea42562ec6bea41b6e4b85a255655dbad554882db31deb3f96
|
3 |
+
size 4907497636
|
model-00015-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c601a3787aa3b128af696e37a504c5c95f6d6c21f50555919bca9bf060f1a1f
|
3 |
+
size 4907497636
|
model-00016-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a39493b8c79791987514d67ef023c58d752466c3dbac8b3131439a905c7b051
|
3 |
+
size 4907497636
|
model-00017-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cea4427e1400405cfc64e7aa8fc4850a850bb7152b86d9bfb07713d38f65708
|
3 |
+
size 4907497636
|
model-00018-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d772e9cc00bd3588ced46e12919afde93e3d43c68df4f8d4ac6624a97e3051cb
|
3 |
+
size 4907497636
|
model-00019-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6e8b98790a4b5e2032949fe87a95e3ec66f7e53ba8414757140ee2c93acda95
|
3 |
+
size 4907497636
|
model-00020-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e562af0b6b2583c91bde3da6ae2ce55b3a875fc0d01bdf3ca2e0bd631e0222e
|
3 |
+
size 4907497636
|
model-00021-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b8e3532126f9a909ce3d4036dcff27ef0b1f5169e668aeced5e6b87084baada
|
3 |
+
size 4907497636
|
model-00022-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50f79e8e6a4b5960816fcab37dd3e1d13d42d04c19b191fb8f402734c9a4e17a
|
3 |
+
size 4970362840
|
model-00023-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8b4e1b2d5a6c4207a079d8ee40382e9c3ee15de326e427df52209377a867129
|
3 |
+
size 4995577824
|
model-00024-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:390978e4078f29189f21a9eebec2760f0ffb5ecd53f248e87c7eecd76f37d086
|
3 |
+
size 4970412220
|
model-00025-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a767e93441304e83ac44893c4973f5753f6e745b51686453479a2836b3a5b12a
|
3 |
+
size 4907472844
|
model-00026-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:962b73f8ac12c614051f8c2f802a849c57551706b56687a624927df1ae1c5b87
|
3 |
+
size 4907497636
|
model-00027-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb1d1d42db049a26bdba4464236d80c039cc17ae4ecc434826f094e0d20d261c
|
3 |
+
size 4907497636
|
model-00028-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43c4d3fdf17d825d843e9ea631ffc7b70fb0d4e36f3e2a328925fa19a5376805
|
3 |
+
size 4907497636
|
model-00029-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edc376b9e39f5d5374a802793463f84c13b9a408cb03b32660be2a37a09152db
|
3 |
+
size 3299988060
|
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 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
3 |
+
size 587404
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|