Upload MixtralForCausalLM
Browse files- config.json +33 -0
- generation_config.json +6 -0
- model-00001-of-00034.safetensors +3 -0
- model-00002-of-00034.safetensors +3 -0
- model-00003-of-00034.safetensors +3 -0
- model-00004-of-00034.safetensors +3 -0
- model-00005-of-00034.safetensors +3 -0
- model-00006-of-00034.safetensors +3 -0
- model-00007-of-00034.safetensors +3 -0
- model-00008-of-00034.safetensors +3 -0
- model-00009-of-00034.safetensors +3 -0
- model-00010-of-00034.safetensors +3 -0
- model-00011-of-00034.safetensors +3 -0
- model-00012-of-00034.safetensors +3 -0
- model-00013-of-00034.safetensors +3 -0
- model-00014-of-00034.safetensors +3 -0
- model-00015-of-00034.safetensors +3 -0
- model-00016-of-00034.safetensors +3 -0
- model-00017-of-00034.safetensors +3 -0
- model-00018-of-00034.safetensors +3 -0
- model-00019-of-00034.safetensors +3 -0
- model-00020-of-00034.safetensors +3 -0
- model-00021-of-00034.safetensors +3 -0
- model-00022-of-00034.safetensors +3 -0
- model-00023-of-00034.safetensors +3 -0
- model-00024-of-00034.safetensors +3 -0
- model-00025-of-00034.safetensors +3 -0
- model-00026-of-00034.safetensors +3 -0
- model-00027-of-00034.safetensors +3 -0
- model-00028-of-00034.safetensors +3 -0
- model-00029-of-00034.safetensors +3 -0
- model-00030-of-00034.safetensors +3 -0
- model-00031-of-00034.safetensors +3 -0
- model-00032-of-00034.safetensors +3 -0
- model-00033-of-00034.safetensors +3 -0
- model-00034-of-00034.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MixtralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": true,
|
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 |
+
"input_jitter_noise": 0.01,
|
13 |
+
"intermediate_size": 6400,
|
14 |
+
"lm_head_bias": true,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"model_type": "mixtral",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_experts_per_tok": 1,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"num_key_value_heads": 8,
|
21 |
+
"num_local_experts": 16,
|
22 |
+
"output_router_logits": false,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"router_aux_loss_coef": 0.0,
|
26 |
+
"router_jitter_noise": 0.01,
|
27 |
+
"sliding_window": 2047,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.45.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32064
|
33 |
+
}
|
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": "4.45.2"
|
6 |
+
}
|
model-00001-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d66f787dbe9fae5e41ca69964bca912cc06ce174a981707fe18ec5f9dac73021
|
3 |
+
size 4992579888
|
model-00002-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c59772574396e413b8da23bb8f4d873e33840a9ca7902d4b40dde6df137c3054
|
3 |
+
size 4991597832
|
model-00003-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9711aee3595431ac5bed8f9c9fd76137c268fd67f9f6c49b1d5e2e1d2a816609
|
3 |
+
size 4991597832
|
model-00004-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:026dff112e50fb6aae23cecb76fc8a4d09d408ff19da1204088313063ca539a0
|
3 |
+
size 4991597840
|
model-00005-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73044a0f99c665b99357065165d2a8103f1a163190cdba1cbc97e9d74bee806
|
3 |
+
size 4991597840
|
model-00006-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1533bacc5e83307c8142b325bb62fb410b1f0ce9e5ff6170edb72bd1cb88c03
|
3 |
+
size 4991597840
|
model-00007-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51ed5c752053e82c10a1f2d4a7807bb621304aff59021c86cd3400d4f8fe3bef
|
3 |
+
size 4991597840
|
model-00008-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f596c713955906fe24e97c9781ea86fca5bbdec6a06683d2276fa817448af350
|
3 |
+
size 4991597840
|
model-00009-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18dd973a15440d8a80c68aa4435ad9b0af1b79285a00cc4c0c2f9009c0d498e2
|
3 |
+
size 4991597840
|
model-00010-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83beb4da86fbaa2a0fdb88a7f2c1caa3c16b793c2b3a05c5451bbb8e99eb124c
|
3 |
+
size 4991597840
|
model-00011-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:105548fbd5944dc6e53e46a2378dee77e912ded1e9a083b2b3fd8ad372f82d33
|
3 |
+
size 4991597872
|
model-00012-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ea41e7355f70a8aebcee9634dfb6379f5536b905e46b2d1315e60bf25d8a8bf
|
3 |
+
size 4991597904
|
model-00013-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efc98722767ade3ca2209f100a88f9d6809f900a91d333d85b9639fc36508837
|
3 |
+
size 4991597904
|
model-00014-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a2d7f6726324cb3c50d8e39e896f9918edc6c66a25188746d082ec3cfb277bd
|
3 |
+
size 4991597904
|
model-00015-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d08aea590d97684e7a0d1f257920e76f9c839a7e392eb244b12e1930b9ba6b2
|
3 |
+
size 4991597904
|
model-00016-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fa535d1d0c2a3534da1fc0bf28a8da36ca6716f5a7777e28766fb7e379eeaa9
|
3 |
+
size 4991597904
|
model-00017-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5fbb868431328624d60ec9229b7588815579ddfbdabfac16d73c8dc3d914194
|
3 |
+
size 4991597904
|
model-00018-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e185651d08f9cd8a9933af76094e00bcc7901b5451e72f123afdf941d329fe98
|
3 |
+
size 4991597904
|
model-00019-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64f423872962b1cf9108d6b07a8f98ce632d06b2df46a3af921d790fef111a3b
|
3 |
+
size 4991597904
|
model-00020-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71af272ba146fbd7e0d30587e1211ecefe3b2adbe3c81fb05c6b42826e9e1ae7
|
3 |
+
size 4991597904
|
model-00021-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a01fcb4d7fca9be1ab5653188791d503996e3e7e826033e11fb2c555cff79a8
|
3 |
+
size 4991597904
|
model-00022-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:510927087a5f6fa2e0e0c7f7dd48fe851e0bf9a39c9c79c91ae0bed18408bd96
|
3 |
+
size 4995504816
|
model-00023-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eebe12b7f7f607be336256f1d88aac2452d1f671b4ed91dacaef456bddc52569
|
3 |
+
size 4924406432
|
model-00024-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7b577c20bebc5519ba8c0b15c4fa7fb70280cd63684ef1999121023603f1b93
|
3 |
+
size 4991597888
|
model-00025-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8403bd7ea9616e4c92246318053c9cb784760cb16a02022a58a86c90f218e944
|
3 |
+
size 4991597888
|
model-00026-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b602d7a91ea7e5ce2b91c5626f18ad9f3f50153193a0be063814adb0695cc6ad
|
3 |
+
size 4991597888
|
model-00027-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fe3460b1f66567497236c0ae8f76d44914b8966bce50910563932eddac82d7d
|
3 |
+
size 4991597888
|
model-00028-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ebda61b718c92372fb3e48b975ade4d05cdb5233dd7912cf6cd607ed8894e8c
|
3 |
+
size 4991597896
|
model-00029-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ed1f376d11c6682fd41e076e8908c92b125a13c47eb1ad589a80e863a540873
|
3 |
+
size 4991597896
|
model-00030-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfc031ac7420c241e288c6018d3c83a13e34c596ba4db3da9c86d905cc3a908f
|
3 |
+
size 4991597896
|
model-00031-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf793c10e72c3203dc171d686d51c078cd2d83fee8825c649cc764f9c589a150
|
3 |
+
size 4991597896
|
model-00032-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56e0d19bfdce198ef7c69fb10bd1a3b12853dcd09bc3e7e4ebf0361434cd35bf
|
3 |
+
size 4991597904
|
model-00033-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95806c7c2e6543044fee3c97974f4ad3eb937a8c8748d5e5a9b791f9d6322c21
|
3 |
+
size 4991597904
|
model-00034-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fec09feb8e18aa7b1eae484c3ef6889322b3dfd3b12aba70aeab36868d140933
|
3 |
+
size 2832434048
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|