Upload MixtralForCausalLM
Browse files- config.json +106 -0
- generation_config.json +6 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TheBloke/Mixtral-8x7B-Instruct-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": 2,
|
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 |
+
"modules_in_block_to_quantize": [
|
39 |
+
[
|
40 |
+
"self_attn.k_proj",
|
41 |
+
"self_attn.v_proj",
|
42 |
+
"self_attn.q_proj"
|
43 |
+
],
|
44 |
+
[
|
45 |
+
"self_attn.o_proj"
|
46 |
+
],
|
47 |
+
[
|
48 |
+
"block_sparse_moe.experts.0.w1",
|
49 |
+
"block_sparse_moe.experts.0.w2",
|
50 |
+
"block_sparse_moe.experts.0.w3"
|
51 |
+
],
|
52 |
+
[
|
53 |
+
"block_sparse_moe.experts.1.w1",
|
54 |
+
"block_sparse_moe.experts.1.w2",
|
55 |
+
"block_sparse_moe.experts.1.w3"
|
56 |
+
],
|
57 |
+
[
|
58 |
+
"block_sparse_moe.experts.2.w1",
|
59 |
+
"block_sparse_moe.experts.2.w2",
|
60 |
+
"block_sparse_moe.experts.2.w3"
|
61 |
+
],
|
62 |
+
[
|
63 |
+
"block_sparse_moe.experts.3.w1",
|
64 |
+
"block_sparse_moe.experts.3.w2",
|
65 |
+
"block_sparse_moe.experts.3.w3"
|
66 |
+
],
|
67 |
+
[
|
68 |
+
"block_sparse_moe.experts.4.w1",
|
69 |
+
"block_sparse_moe.experts.4.w2",
|
70 |
+
"block_sparse_moe.experts.4.w3"
|
71 |
+
],
|
72 |
+
[
|
73 |
+
"block_sparse_moe.experts.5.w1",
|
74 |
+
"block_sparse_moe.experts.5.w2",
|
75 |
+
"block_sparse_moe.experts.5.w3"
|
76 |
+
],
|
77 |
+
[
|
78 |
+
"block_sparse_moe.experts.6.w1",
|
79 |
+
"block_sparse_moe.experts.6.w2",
|
80 |
+
"block_sparse_moe.experts.6.w3"
|
81 |
+
],
|
82 |
+
[
|
83 |
+
"block_sparse_moe.experts.7.w1",
|
84 |
+
"block_sparse_moe.experts.7.w2",
|
85 |
+
"block_sparse_moe.experts.7.w3"
|
86 |
+
]
|
87 |
+
],
|
88 |
+
"pad_token_id": null,
|
89 |
+
"quant_method": "gptq",
|
90 |
+
"sym": true,
|
91 |
+
"tokenizer": null,
|
92 |
+
"true_sequential": true,
|
93 |
+
"use_cuda_fp16": false,
|
94 |
+
"use_exllama": true
|
95 |
+
},
|
96 |
+
"rms_norm_eps": 1e-05,
|
97 |
+
"rope_theta": 1000000.0,
|
98 |
+
"router_aux_loss_coef": 0.02,
|
99 |
+
"router_jitter_noise": 0.0,
|
100 |
+
"sliding_window": 4096,
|
101 |
+
"tie_word_embeddings": false,
|
102 |
+
"torch_dtype": "float16",
|
103 |
+
"transformers_version": "4.40.2",
|
104 |
+
"use_cache": true,
|
105 |
+
"vocab_size": 32000
|
106 |
+
}
|
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": "4.40.2"
|
6 |
+
}
|
model-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c47108bd055998f6f21f87ce572e2cb5a8e3f0f069825458b6d5a37fb4d2324
|
3 |
+
size 4973490648
|
model-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa547a6e9fea7fd5d0c524412a2493db8d8d725585b3662699a49bc59c70e752
|
3 |
+
size 4976328272
|
model-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d78e5e9e9a775b305ab283051f7bc02f38339c50760c19827e8601fba0b62227
|
3 |
+
size 4976323664
|
model-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e5ca20003ac33f8e93e725d48ca023f2127f3c542eade8669d990e6dfa54bec
|
3 |
+
size 4995156968
|
model-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:884385c30ac1f9ef490e7dae2481d8e6cd92e4d5e1d3f89f97ef8106a94134f7
|
3 |
+
size 3890241880
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|