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": 4,
|
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:e510dc5381a68a100d2fdc6e6ee6eecf0496aa8f2bcae50dddf4b41b01b05f41
|
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:e9f91409cd0f633e0fecae42d0bd0d7df2eed1a1d864f11787d702903709460e
|
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:be14397d34cabace1a9181cfa36257397534951ef0a9827be45e6ff47b99b5cf
|
3 |
+
size 4991597832
|
model-00004-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fcd71bd04c3ea7586bf9fc9d6b240a9956a4bb445a9d880914bbfb5bf3bb515
|
3 |
+
size 4991597840
|
model-00005-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d9c0646d2a4c94855949b25741583a24fc2d1b497a82034dbd377595e527d4b
|
3 |
+
size 4991597840
|
model-00006-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a75097cc14d0fe3d4d03f6c184da2b9be9369f8746a20011d22f21bf008e3e7
|
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:e07d78f0efb857ab6bfe617336bab61fb4b6384d27ffaf02f65ffd7f104f99bb
|
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:de437e79c35052a8f76fdd8fb68370c1a2e13bffa22ad3951869be581abafe89
|
3 |
+
size 4991597840
|
model-00009-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:694938a8d69813f073628bf3f4025fb04e4b253dc3d1b8ee08a72e697d8c7abc
|
3 |
+
size 4991597840
|
model-00010-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a98253770f1fbabc173deacde660abb7acdbc365be2fd4fa663295fea858ebc
|
3 |
+
size 4991597840
|
model-00011-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98dec1d7049a6a9a5a7060a908b6b6e33ffa79b0e00490ac851c3095c7574ba9
|
3 |
+
size 4991597872
|
model-00012-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23eab022cdf41861d1f31188f31ed1aaf13eb0f7f30817f54e12db014470f58f
|
3 |
+
size 4991597904
|
model-00013-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ada4373f1b8c27074e0309976ab6e944c28fd0128d1af400398f1eaae399563
|
3 |
+
size 4991597904
|
model-00014-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ac45dc9e71358685537ce8241372e9b6c0e5dc458de3ebccab423b85153e897
|
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:a0ece1e5a5f932160d3955b15871b843cc441e9057b6132aebe3c71539680bdc
|
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:ac9d824cdb9a3e72d0d9057afb684157aff4c1771b9f7b2fe65e4ef807c553da
|
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:a387ce5e3d098ed09ec07d79fe7e1e35f3a81fe43f2b39484fc0b06b50cf3d0e
|
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:ea11b86376d72dd52a0173cd0ce614eb7550c4e36188d93238db85877aa7edad
|
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:db716896391b97c0a247adefdfef71e6588f22cedd455d75f08ee4824e5cf3b5
|
3 |
+
size 4991597904
|
model-00020-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:876ed642a25cc23f22c3c22ad7a5f854a7f822eebe285741a18ce325cbf971fe
|
3 |
+
size 4991597904
|
model-00021-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07fc4f6450e351665d39c8dbf4078a504bebe23435d5dbbd2f117982b6e1f03c
|
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:db7c2e13da4d5a25e6c3e4f21146adc14ee2798d895e1d62256225cf5f2bdc5c
|
3 |
+
size 4995504816
|
model-00023-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64b8307381825d3afd0ac94947cb2c25a9d1d46f14cbb294ad0baacf921827ae
|
3 |
+
size 4924406432
|
model-00024-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5544cd2bce816bffa1652bd70017977b06bac4ac7f79ea0d9931b30f7b6ab8e4
|
3 |
+
size 4991597888
|
model-00025-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5041a8669a142b0484ccd570d5b46b4e7c73c4fee94e9dfeeeeefe2b5e49829f
|
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:a531e2856e48453f2c49cf30f7592b5d5fa2ef62c3f4c4323a98eab0678696dd
|
3 |
+
size 4991597888
|
model-00027-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0202bf4356331e48896139136266d24ea04bac47a6bbc241dc2302a14f3fa4ff
|
3 |
+
size 4991597888
|
model-00028-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27fd40e30d56d5a0caea5075c5107136f7765b98a3f60b98b5fc4e14339e645b
|
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:a48f6a6f0a7d5a325a965d3bee49a73bb66299495c7e6cd17d29be369a2786a6
|
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:b900a3719ad5ca51058fb2cd96f0098ef63a9f918daef0e983b551b8fe57fc79
|
3 |
+
size 4991597896
|
model-00031-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8af14d828546fa8019866b7f40ab1f135aa3b18106a4f92d1a5f703155dff5a6
|
3 |
+
size 4991597896
|
model-00032-of-00034.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:263644427b139ad82d61c398ca795adaa4f4289d8e5e359203bce41f7322bae2
|
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:a80be7647e31fa09fe87b194317c3e9490e204db0529f120eaa6a285ba55e13f
|
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:e3d3c823723115f283e2aed87ebf513d6c8a9d5175f5a4455711e7597f67b13e
|
3 |
+
size 2832434048
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|