Upload MixtralForCausalLM
Browse files- config.json +36 -0
- generation_config.json +6 -0
- model-00001-of-00035.safetensors +3 -0
- model-00002-of-00035.safetensors +3 -0
- model-00003-of-00035.safetensors +3 -0
- model-00004-of-00035.safetensors +3 -0
- model-00005-of-00035.safetensors +3 -0
- model-00006-of-00035.safetensors +3 -0
- model-00007-of-00035.safetensors +3 -0
- model-00008-of-00035.safetensors +3 -0
- model-00009-of-00035.safetensors +3 -0
- model-00010-of-00035.safetensors +3 -0
- model-00011-of-00035.safetensors +3 -0
- model-00012-of-00035.safetensors +3 -0
- model-00013-of-00035.safetensors +3 -0
- model-00014-of-00035.safetensors +3 -0
- model-00015-of-00035.safetensors +3 -0
- model-00016-of-00035.safetensors +3 -0
- model-00017-of-00035.safetensors +3 -0
- model-00018-of-00035.safetensors +3 -0
- model-00019-of-00035.safetensors +3 -0
- model-00020-of-00035.safetensors +3 -0
- model-00021-of-00035.safetensors +3 -0
- model-00022-of-00035.safetensors +3 -0
- model-00023-of-00035.safetensors +3 -0
- model-00024-of-00035.safetensors +3 -0
- model-00025-of-00035.safetensors +3 -0
- model-00026-of-00035.safetensors +3 -0
- model-00027-of-00035.safetensors +3 -0
- model-00028-of-00035.safetensors +3 -0
- model-00029-of-00035.safetensors +3 -0
- model-00030-of-00035.safetensors +3 -0
- model-00031-of-00035.safetensors +3 -0
- model-00032-of-00035.safetensors +3 -0
- model-00033-of-00035.safetensors +3 -0
- model-00034-of-00035.safetensors +3 -0
- model-00035-of-00035.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"lora_rank": 16,
|
16 |
+
"max_position_embeddings": 4096,
|
17 |
+
"model_type": "mixtral",
|
18 |
+
"num_attention_heads": 32,
|
19 |
+
"num_experts_per_tok": 2,
|
20 |
+
"num_hidden_layers": 32,
|
21 |
+
"num_key_value_heads": 8,
|
22 |
+
"num_local_experts": 16,
|
23 |
+
"output_router_logits": false,
|
24 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"router_aux_loss_coef": 0.0,
|
27 |
+
"router_jitter_noise": 0.01,
|
28 |
+
"separate_lora": false,
|
29 |
+
"sliding_window": 2047,
|
30 |
+
"tie_word_embeddings": false,
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.45.2",
|
33 |
+
"use_cache": true,
|
34 |
+
"use_lora": true,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
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-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a951abcf896c9dcd42a5e771cedfb8a2f48f636a22db8dddf9bceddde9f8c22e
|
3 |
+
size 4992579888
|
model-00002-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b243ece871e3cb90ca317eabeaf90033e10a50dd72a370ed10579b1e27398d0
|
3 |
+
size 4918996520
|
model-00003-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c427c3983725f73bb617df8f81566e43c0fe41535be352384db517905f482259
|
3 |
+
size 4918996720
|
model-00004-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5abac075c696aa917cb708af1fc5d1177e5329dc91a84a630e810f4f2b7a0f31
|
3 |
+
size 4918996720
|
model-00005-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8720d31a6644bd220fdc10fded00860dc55197b6692fd459954fc660bfea277
|
3 |
+
size 4918996720
|
model-00006-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73c55e0df22f5a64b55bccf6546a8f70b3a3b6834ce8eb209197b44edf060a75
|
3 |
+
size 4918996728
|
model-00007-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57730a8d66a360bb159e7e1c6d349abb1c31689856c2f75144b9c4c13ff396c5
|
3 |
+
size 4918996728
|
model-00008-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c468d6a233145689790745e79845ea070707249292a334ee8b620faed6a6a572
|
3 |
+
size 4918996728
|
model-00009-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34a56a4ec2ea555a20313939c39aec89778584183b89b2964517ac8bddeeed78
|
3 |
+
size 4918996728
|
model-00010-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50bdeb77f137a60387c3e9d239080e996bbb73b81795dd13f5a6d886cabd5367
|
3 |
+
size 4918996728
|
model-00011-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b788facfbc8180e21fa0c1c2db9695efa3c53c0fe33856f76c6cf3d360681db2
|
3 |
+
size 4918996744
|
model-00012-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a696f52594a4e9c26fc9b47df03a360134e82afb6f22cfa203815f9754123b0a
|
3 |
+
size 4918996880
|
model-00013-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e33c551953fad022f26387db966ec7ea11e04d9f2fea269e1996b62fb250763
|
3 |
+
size 4918996880
|
model-00014-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88600156a76c51623d91484978e5e45d3beee4768fdf58299a0be819382e92ba
|
3 |
+
size 4918996880
|
model-00015-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fda2893eda1b5e06fb81b10165279e9a4c19ae804b058eeecff3b3099310c6c8
|
3 |
+
size 4956466872
|
model-00016-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cb2cee0f0996f0b2aa944afb520f285efdf95a3eb465d596ebdd76d3fda28f8
|
3 |
+
size 4995701080
|
model-00017-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8b8aecf2678f79261a6d7d42c3acffaeb91080be5871c0399009d1c05e9b86e
|
3 |
+
size 4918996672
|
model-00018-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7b8b7c1334758f1084881cc1799e2df3ee60adafbd381156584cba4af693622
|
3 |
+
size 4918996672
|
model-00019-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:286e269b05571656024a31f5c41b8aa63cc3b1b8e1f6039dda3888505be7d927
|
3 |
+
size 4918996672
|
model-00020-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a38cdb9e3933b8ec128467f34cade433ffb47046e5af883eb7a6db3b0b37a1c4
|
3 |
+
size 4918996872
|
model-00021-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71817ff8e86347a9a059f32478d81bf2584fd2db718d8d001c5d43382561cf64
|
3 |
+
size 4918996872
|
model-00022-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cef34ffdbaf35052ef99696aacebac6d33af2791ca7e01f81afadf71ca6a1044
|
3 |
+
size 4918996880
|
model-00023-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f83fb383e9dfa0d1007acc69b14506833930001d720b77e3697cacfb95a689b
|
3 |
+
size 4918996880
|
model-00024-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da27e8d2c0137674af013cfaaa5ab0394af56cda070504c65a0c570537b002fe
|
3 |
+
size 4918996880
|
model-00025-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efacda25e37b87203c0a818be97fbe64fda88335f9fbff38f1c5c90544ff21c4
|
3 |
+
size 4918996880
|
model-00026-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcaa256dea118fc46bc0fb75a33062fc5bc49b65dfadbe01828629d0549d813d
|
3 |
+
size 4918996880
|
model-00027-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a113d1859aba732021049e77838cece9c0af897e5e4310729afdd59f621c6e5
|
3 |
+
size 4918996880
|
model-00028-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4bbb39c81be63d541f2eb186e8840796c9dc71ef50830efc1841c3764628b42
|
3 |
+
size 4918996880
|
model-00029-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bde1740d3a9f1d473be1a7474f2baaeb2cec6b0ddecf445f4d55698e3e26c99d
|
3 |
+
size 4918996880
|
model-00030-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ac1ca88f4e847440cbb550a13038ca060b15a49d33af612411d60f7e4b32ef7
|
3 |
+
size 4918996880
|
model-00031-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f02b36964d5f0e170d87dbc2232fa3eacce4b32930be93a7e57bcf54899b3800
|
3 |
+
size 4918996880
|
model-00032-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90b09e6a0b3cfd48f2e8af46f5a9c47cbe966516bdaa3f85f48311110edbb82f
|
3 |
+
size 4956466872
|
model-00033-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b8f3ff9f05c0964dfd8715651e21749b0bac2dbf17720a7e42dc45f47f60696
|
3 |
+
size 4995701080
|
model-00034-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e10e6814ae1057f43454d9844c6cd85e3bfaafe14585208ad68bbb4e1a89881
|
3 |
+
size 4918996672
|
model-00035-of-00035.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bd148c5488eb37d7bf7793e074e4803db5b1906bb6c7937e0b8dd464ba64cf8
|
3 |
+
size 977251400
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|