Upload MixtralForCausalLM
Browse files- config.json +44 -0
- generation_config.json +6 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
|
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 |
+
"quantization_config": {
|
22 |
+
"_load_in_4bit": true,
|
23 |
+
"_load_in_8bit": false,
|
24 |
+
"bnb_4bit_compute_dtype": "float16",
|
25 |
+
"bnb_4bit_quant_type": "fp4",
|
26 |
+
"bnb_4bit_use_double_quant": false,
|
27 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
+
"llm_int8_has_fp16_weight": false,
|
29 |
+
"llm_int8_skip_modules": null,
|
30 |
+
"llm_int8_threshold": 6.0,
|
31 |
+
"load_in_4bit": true,
|
32 |
+
"load_in_8bit": false,
|
33 |
+
"quant_method": "bitsandbytes"
|
34 |
+
},
|
35 |
+
"rms_norm_eps": 1e-05,
|
36 |
+
"rope_theta": 1000000.0,
|
37 |
+
"router_aux_loss_coef": 0.02,
|
38 |
+
"sliding_window": null,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"torch_dtype": "float16",
|
41 |
+
"transformers_version": "4.38.1",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 32000
|
44 |
+
}
|
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": "4.38.1"
|
6 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8fede7d0d42c2152691e6ea84fd6062a7cc012ee659f56edd2bcd1e7b82e844
|
3 |
+
size 4995199930
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d351c581c1cf26de7fbee580b992c2d74f293173972091090097b7d56fa4080e
|
3 |
+
size 4997319282
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5538a508bbf0698e59beabb1876e18db7a9e20d7a601c48e0410b5e6a0cac1f2
|
3 |
+
size 4987920138
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59e1b2c9824830648f8cf9d8591d71c67c7aaa0716102441b69e4a8e7da814b7
|
3 |
+
size 4997319794
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6868eb896c5920a058ea84c4a46b20dbba5238cd66f7c38c14cc23f086f4b08f
|
3 |
+
size 4997319794
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06eeaa0f7c86624f9eca4ce075ebc76d9b880bf9bb84447c8a6e0d576c13bf08
|
3 |
+
size 1673095094
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|