Upload 678 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- config.json +31 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00672.bin +3 -0
- pytorch_model-00002-of-00672.bin +3 -0
- pytorch_model-00003-of-00672.bin +3 -0
- pytorch_model-00004-of-00672.bin +3 -0
- pytorch_model-00005-of-00672.bin +3 -0
- pytorch_model-00006-of-00672.bin +3 -0
- pytorch_model-00007-of-00672.bin +3 -0
- pytorch_model-00008-of-00672.bin +3 -0
- pytorch_model-00009-of-00672.bin +3 -0
- pytorch_model-00010-of-00672.bin +3 -0
- pytorch_model-00011-of-00672.bin +3 -0
- pytorch_model-00012-of-00672.bin +3 -0
- pytorch_model-00013-of-00672.bin +3 -0
- pytorch_model-00014-of-00672.bin +3 -0
- pytorch_model-00015-of-00672.bin +3 -0
- pytorch_model-00016-of-00672.bin +3 -0
- pytorch_model-00017-of-00672.bin +3 -0
- pytorch_model-00018-of-00672.bin +3 -0
- pytorch_model-00019-of-00672.bin +3 -0
- pytorch_model-00020-of-00672.bin +3 -0
- pytorch_model-00021-of-00672.bin +3 -0
- pytorch_model-00022-of-00672.bin +3 -0
- pytorch_model-00023-of-00672.bin +3 -0
- pytorch_model-00024-of-00672.bin +3 -0
- pytorch_model-00025-of-00672.bin +3 -0
- pytorch_model-00026-of-00672.bin +3 -0
- pytorch_model-00027-of-00672.bin +3 -0
- pytorch_model-00028-of-00672.bin +3 -0
- pytorch_model-00029-of-00672.bin +3 -0
- pytorch_model-00030-of-00672.bin +3 -0
- pytorch_model-00031-of-00672.bin +3 -0
- pytorch_model-00032-of-00672.bin +3 -0
- pytorch_model-00033-of-00672.bin +3 -0
- pytorch_model-00034-of-00672.bin +3 -0
- pytorch_model-00035-of-00672.bin +3 -0
- pytorch_model-00036-of-00672.bin +3 -0
- pytorch_model-00037-of-00672.bin +3 -0
- pytorch_model-00038-of-00672.bin +3 -0
- pytorch_model-00039-of-00672.bin +3 -0
- pytorch_model-00040-of-00672.bin +3 -0
- pytorch_model-00041-of-00672.bin +3 -0
- pytorch_model-00042-of-00672.bin +3 -0
- pytorch_model-00043-of-00672.bin +3 -0
- pytorch_model-00044-of-00672.bin +3 -0
- pytorch_model-00045-of-00672.bin +3 -0
- pytorch_model-00046-of-00672.bin +3 -0
- pytorch_model-00047-of-00672.bin +3 -0
- pytorch_model-00048-of-00672.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"MixtralForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"head_dim": 128,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 8192,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 91552,
|
13 |
+
"max_position_embeddings": 65536,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 64,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 16,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 14,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000,
|
23 |
+
"router_aux_loss_coef": 0.001,
|
24 |
+
"router_jitter_noise": 0.0,
|
25 |
+
"sliding_window": null,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.49.0",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32000
|
31 |
+
}
|
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": "4.49.0"
|
6 |
+
}
|
pytorch_model-00001-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06b53736c64da64bce5a3f2bd0911311358f35239737447ae3e83dc667cab9dc
|
3 |
+
size 1588
|
pytorch_model-00002-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7dd1acf1977eb8a8562daf3e547accb775af643fa9754f7e13ee60c33fffb2f
|
3 |
+
size 1140
|
pytorch_model-00003-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c7da0263eaead4628bc48f6966a2482a7dff40ae7a3d44989e013a8b18cfbb3
|
3 |
+
size 1140
|
pytorch_model-00004-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a6422b0f3610657de545aec5aceec58c0fc349fe741bf2599f2c8c9ef3c5b15
|
3 |
+
size 1140
|
pytorch_model-00005-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17d1bd0e4deba7e1d13599774db3e2b1f2bae89823190bff521e50bc66070148
|
3 |
+
size 1140
|
pytorch_model-00006-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:983b898cfbca28f84f065a0699b8b040f8a298e177902900ce4cc732baf53340
|
3 |
+
size 1140
|
pytorch_model-00007-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36dd50d07ca2bd640c841d3b425872e2462db662d48923d38494b705b3d2f6b7
|
3 |
+
size 1140
|
pytorch_model-00008-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc62a072a5f7997119e35a28ba462bd8bc8af2d5d6e32f90e683147dbdfab29b
|
3 |
+
size 1140
|
pytorch_model-00009-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21d21c73216c847f7b62486c54c6eb7a3f7ba1c5b8c1679668356be1aad660c3
|
3 |
+
size 1140
|
pytorch_model-00010-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18bea6790614d4f0f8a1c020c2f6c63bc8f3317db503a06191e91366cd12bd17
|
3 |
+
size 1140
|
pytorch_model-00011-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7962e60160d1e8328bf5d32e9db72ec2ec029b4487b34650b26f3790fdfbbef1
|
3 |
+
size 1140
|
pytorch_model-00012-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0780f0eb8c98c00bbfc798cda49f0e55dcc8604db7de4f34629a4424eb936020
|
3 |
+
size 1140
|
pytorch_model-00013-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e33aa2205ce188fabdfbaf55fb22411474fd49416cef948dab1b11505429e19
|
3 |
+
size 1140
|
pytorch_model-00014-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:808e03a5fca72337a4cb0759e5a8ddcd8f2b9ebc7ffc4ca689d3ec6788dfe5f8
|
3 |
+
size 1140
|
pytorch_model-00015-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab2382bd5c3794552fb0837b72e05c83e1dbe841df27cc3c4097e763ca9ecb9c
|
3 |
+
size 1140
|
pytorch_model-00016-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65b21bc2eb11bb16736486752f88d82d56774a5c5c913fd070d46be6ce8c375a
|
3 |
+
size 1140
|
pytorch_model-00017-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fb086c0e6e0196016b8d8f190a20e90d3d93991fbd3ad2a9f6a7da790f3dbde
|
3 |
+
size 1140
|
pytorch_model-00018-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85a556badff066985c20f2c7d46d7bbdf0398e6ad4e6de3edd56b6eae7a80a96
|
3 |
+
size 1140
|
pytorch_model-00019-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55611b62ecaa251bd3da06b5837e8f99d2bdd9880da05bfc8d180eaceeaef9e4
|
3 |
+
size 1140
|
pytorch_model-00020-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b72162226474864e5e611e675e5f1837c4f9bdd42dfff840c27c6976736cd1c
|
3 |
+
size 1140
|
pytorch_model-00021-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f15abf4bd03820aaf8a4c02ef448cf2fd515438c5456e0602532c9030c01f8d
|
3 |
+
size 1140
|
pytorch_model-00022-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31a41f77ac210d2ff2506cae51c4fd7f98f68bc4358856b1d5f873ff6851a300
|
3 |
+
size 1140
|
pytorch_model-00023-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aaffee59c25128534f30587557a94ec1f72d69af19abb5eefe792e73e2a70bed
|
3 |
+
size 1140
|
pytorch_model-00024-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05d185036acfb59c8abec7bbb0674fa03ab6a39604d56eadd9f250651cc20254
|
3 |
+
size 1140
|
pytorch_model-00025-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2ed0d7720f2322b0ed36b0f0a247b53427f52a447dd9abdd939104e358419cc
|
3 |
+
size 1140
|
pytorch_model-00026-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1eb73c08ec042b900da98f890c3452c5898dcf8acab62503b1d71dc90a3eb616
|
3 |
+
size 1140
|
pytorch_model-00027-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9535c1ce5f47114af2e0c1a33d8706ccc1a2d2403cde811307ad61459c614bfc
|
3 |
+
size 1140
|
pytorch_model-00028-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd7ee0af5ebf6e796fdbbf5f7143662f52543aaf2afc9ac7048fc1d6256d6fd3
|
3 |
+
size 1140
|
pytorch_model-00029-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de600c86f50ed32f53aeafba43472af7c50246e22d04f4bde066193d681c218f
|
3 |
+
size 1140
|
pytorch_model-00030-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9dd944291972c62a9ebe4d8649548b038475a8dca23be2df8ee54258df5c7b46
|
3 |
+
size 1140
|
pytorch_model-00031-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea3d90c59f50fa76b41939451453a2e6ca4d084ca0d7bb8deecad448ff44dac9
|
3 |
+
size 1140
|
pytorch_model-00032-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3e47bcbbb5e65e81bf569a170157f349c603508a9ddf7a1f10d1ebfb60aba4a
|
3 |
+
size 1140
|
pytorch_model-00033-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5a8c4ae98dc6ab0add72f2f489fcdfd193fb1b7b892bed2a3720abafe7a58d8
|
3 |
+
size 1140
|
pytorch_model-00034-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8d11b6848d82e44aabdd97ac5a92eb1dcfad67a84f2bf6666d65b5f8d517d59
|
3 |
+
size 1140
|
pytorch_model-00035-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4a464a4659e4f5596b58fecb933c80496191fbfac728a8e59805581a22878da
|
3 |
+
size 1140
|
pytorch_model-00036-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f88630ddb65671830acf4007603cca43b57b7cc6bab0bf9edda8fe42bf978c6
|
3 |
+
size 1140
|
pytorch_model-00037-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2e5cfde30a9696d70c108eed27b497132254ccf55a5ec6931c5af30ec8af1a3
|
3 |
+
size 1140
|
pytorch_model-00038-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5e32db11da0966cd1ff7e8b455b95cf45c365bbf10cfba6be50c38c0875f640
|
3 |
+
size 1140
|
pytorch_model-00039-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:963203d1269a7f4144f6830154d5248d41cf68ec18a00c42a8276504023e29ec
|
3 |
+
size 1140
|
pytorch_model-00040-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c4ff1fa1ef84e638c9434a9a14e6e418e3417e7ecea30343967c653bd2bb8dd
|
3 |
+
size 1140
|
pytorch_model-00041-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a521147ff0fcd2133db747d86d36e0e30b1296fe3306a9ffb14126a8b7545bf3
|
3 |
+
size 1140
|
pytorch_model-00042-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c56581c39a35f895470b0aed53f01f6e5808108b76d6478220500cf446e0438e
|
3 |
+
size 1652
|
pytorch_model-00043-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d7cc12582a77cda1cc3c536315317eda144c07c537bdb6e937d06ce0947ae43
|
3 |
+
size 1140
|
pytorch_model-00044-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47d08f552ad7bc1bfec196692c9835a6cb0a3c7d615f8a1c2a0a16024c91f67e
|
3 |
+
size 1140
|
pytorch_model-00045-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0155243eddc4433901a27940d6f1a937cc1bda0d588a0bf2e71c012b8ee3e14
|
3 |
+
size 1140
|
pytorch_model-00046-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:229430257e494d01bc8e78b99eb779c6eb45ee8b1db265ac112d43ff522b4156
|
3 |
+
size 1140
|
pytorch_model-00047-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82cb09ae6132796d253dac1d0b246af35c46ad2604e908752f697b278a545881
|
3 |
+
size 1140
|
pytorch_model-00048-of-00672.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d17a3d8c8100a856a3cea0b699d83fe9a412d3cd3b9f368c159edf433c9d625
|
3 |
+
size 1140
|