Daryoush Vaziri
commited on
Commit
•
56b0c40
1
Parent(s):
a7dc235
Upload 7 files
Browse files- config.json +30 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00019.bin +3 -0
- pytorch_model-00002-of-00019.bin +3 -0
- pytorch_model-00003-of-00019.bin +3 -0
- pytorch_model-00004-of-00019.bin +3 -0
- pytorch_model-00005-of-00019.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_theta": 1000000.0,
|
23 |
+
"router_aux_loss_coef": 0.02,
|
24 |
+
"sliding_window": 4096,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.36.0.dev0",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
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.dev0"
|
6 |
+
}
|
pytorch_model-00001-of-00019.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfa1db7f11c567949445dd76afc5e761a3fcaf832ae5d3a1f82fda75f2f0592d
|
3 |
+
size 4892820801
|
pytorch_model-00002-of-00019.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a105e669e6a1c0ac22246aca46b24ee1c481e9c6f5f25e02719bb3a843424376
|
3 |
+
size 4983016125
|
pytorch_model-00003-of-00019.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56cc90354ef7eeeba780451a020800229d1722225c88fc42453f9382d9517e05
|
3 |
+
size 4983016209
|
pytorch_model-00004-of-00019.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:415f0a9beb5f7c50d81abef2041728e2b85599290134bd34d4579d3ea0455916
|
3 |
+
size 4899045759
|
pytorch_model-00005-of-00019.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f2f37aef87fab026be658783bdc4a79cf5fa1d3ea675fcc8efa8e7dccb292b5
|
3 |
+
size 4983016161
|