Upload MixtralForCausalLM
Browse files- config.json +55 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00013.bin +3 -0
- pytorch_model-00002-of-00013.bin +3 -0
- pytorch_model-00003-of-00013.bin +3 -0
- pytorch_model-00004-of-00013.bin +3 -0
- pytorch_model-00005-of-00013.bin +3 -0
- pytorch_model-00006-of-00013.bin +3 -0
- pytorch_model-00007-of-00013.bin +3 -0
- pytorch_model-00008-of-00013.bin +3 -0
- pytorch_model-00009-of-00013.bin +3 -0
- pytorch_model-00010-of-00013.bin +3 -0
- pytorch_model-00011-of-00013.bin +3 -0
- pytorch_model-00012-of-00013.bin +3 -0
- pytorch_model-00013-of-00013.bin +3 -0
- pytorch_model.bin.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TheBloke/Mixtral-8x7B-v0.1-GPTQ",
|
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": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mixtral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
+
"num_hidden_layers": 32,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"num_local_experts": 8,
|
20 |
+
"output_router_logits": false,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"quantization_config": {
|
24 |
+
"batch_size": 1,
|
25 |
+
"bits": 4,
|
26 |
+
"block_name_to_quantize": null,
|
27 |
+
"cache_block_outputs": true,
|
28 |
+
"damp_percent": 0.1,
|
29 |
+
"dataset": null,
|
30 |
+
"desc_act": true,
|
31 |
+
"exllama_config": {
|
32 |
+
"version": 1
|
33 |
+
},
|
34 |
+
"group_size": -1,
|
35 |
+
"max_input_length": null,
|
36 |
+
"model_seqlen": null,
|
37 |
+
"module_name_preceding_first_block": null,
|
38 |
+
"pad_token_id": null,
|
39 |
+
"quant_method": "gptq",
|
40 |
+
"sym": true,
|
41 |
+
"tokenizer": null,
|
42 |
+
"true_sequential": true,
|
43 |
+
"use_cuda_fp16": false,
|
44 |
+
"use_exllama": true
|
45 |
+
},
|
46 |
+
"rms_norm_eps": 1e-05,
|
47 |
+
"rope_theta": 1000000.0,
|
48 |
+
"router_aux_loss_coef": 0.02,
|
49 |
+
"sliding_window": 4096,
|
50 |
+
"tie_word_embeddings": false,
|
51 |
+
"torch_dtype": "float16",
|
52 |
+
"transformers_version": "4.36.0",
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 32000
|
55 |
+
}
|
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": "4.36.0"
|
6 |
+
}
|
pytorch_model-00001-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:635ecfcb9ab48a8ba428e8649d4f1011dc16cb062ac9b17fc1280423bd697f2e
|
3 |
+
size 1974230553
|
pytorch_model-00002-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2487b1b769c0da6aebb28bd55cedb971e33cfa63773f048013e5770d13eb2125
|
3 |
+
size 1977101423
|
pytorch_model-00003-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa1cada906e583988ed1824a019e5e9574214b869ee0a8e709bdcaf31ae4848a
|
3 |
+
size 1985397728
|
pytorch_model-00004-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d55113257539380d69c183d7dcc481a50eb52a7f187f394bcef7660c6dd8e040
|
3 |
+
size 1977096367
|
pytorch_model-00005-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62b0348488496fa026dfd1341ca486d5038dcbeb66e519762f61b30605876110
|
3 |
+
size 1977096687
|
pytorch_model-00006-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0f6bbd9b235b2a25eea1cf0f638b098b23b39b2cb5fd16efcbd8cd73eb5de72
|
3 |
+
size 1985398112
|
pytorch_model-00007-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9b107a6c169d008798a8949cf3451a9b87e8416bb288002dc0a6e8545d37999
|
3 |
+
size 1977101807
|
pytorch_model-00008-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612a3c94d7a115edd595b54c5d4b64402cf3d03c91b6a718a77ecd2e86abb099
|
3 |
+
size 1977096687
|
pytorch_model-00009-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fbcfa591b7d2c3782a9a30205e8e0d7852ebae8d5f7e03a95e6b66074147433
|
3 |
+
size 1977096687
|
pytorch_model-00010-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82f7b1aa4eec490495b9fdfa9dfa59aee1aaf72c7dbe8db128abf8d577669b52
|
3 |
+
size 1985398112
|
pytorch_model-00011-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4c29c956c5b7ae84ba53cccdb8e963d998047768cf03cc1c57296668f00b343
|
3 |
+
size 1977101807
|
pytorch_model-00012-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef2e0db04f08620944beb8d94ecef72a3e2c6653d22a9b6fc6570873df53f1c
|
3 |
+
size 1779368268
|
pytorch_model-00013-of-00013.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cc31b25c893543ff4fa75a10cc9ed2df2b5ccfdf1d67f2decffb1030b4a4271
|
3 |
+
size 262145413
|
pytorch_model.bin.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|