Upload MixtralForCausalLM
Browse files- config.json +42 -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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mixtral-8x7B-Instruct-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 |
+
"bnb_4bit_compute_dtype": "float32",
|
23 |
+
"bnb_4bit_quant_type": "fp4",
|
24 |
+
"bnb_4bit_use_double_quant": false,
|
25 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
26 |
+
"llm_int8_has_fp16_weight": false,
|
27 |
+
"llm_int8_skip_modules": null,
|
28 |
+
"llm_int8_threshold": 6.0,
|
29 |
+
"load_in_4bit": true,
|
30 |
+
"load_in_8bit": false,
|
31 |
+
"quant_method": "bitsandbytes"
|
32 |
+
},
|
33 |
+
"rms_norm_eps": 1e-05,
|
34 |
+
"rope_theta": 1000000.0,
|
35 |
+
"router_aux_loss_coef": 0.02,
|
36 |
+
"sliding_window": null,
|
37 |
+
"tie_word_embeddings": false,
|
38 |
+
"torch_dtype": "float16",
|
39 |
+
"transformers_version": "4.37.0.dev0",
|
40 |
+
"use_cache": true,
|
41 |
+
"vocab_size": 32000
|
42 |
+
}
|
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": "4.37.0.dev0"
|
6 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:454e6b733eca681ac5b408ed364cb46b3a9913abf0c94d50df4604318f3a8a90
|
3 |
+
size 4995199930
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f9d560f369c801ab95f8e8df992430a55444e90f46f801a1f7d5e99bc76cf5c
|
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:e43c4a29f4aeb419c1c57252dd0897fa81d12fde02997a193b32f2c29e4a4e9b
|
3 |
+
size 4987920138
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00971c5d91f4b191abc0ef06a515b4d270016ad5f9025ce5428c0d1aa21220d7
|
3 |
+
size 4997319794
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9809aa45f8874bb467706466da2a280e28466693f316753088cd8f5146d471b2
|
3 |
+
size 4997319794
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e1866db8d6a88c5e162019f1988f2dfd1a21288052bedb7738ccc9ddaa3a4ca
|
3 |
+
size 1673095094
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|