xxchenxx commited on
Commit ·
58ed540
1
Parent(s): e13671f
First model version
Browse files- config.json +41 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00006.bin +3 -0
- pytorch_model-00002-of-00006.bin +3 -0
- pytorch_model-00003-of-00006.bin +3 -0
- pytorch_model-00004-of-00006.bin +3 -0
- pytorch_model-00005-of-00006.bin +3 -0
- pytorch_model-00006-of-00006.bin +3 -0
- pytorch_model.bin.index.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "fairseq-moe-15b",
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"FSGPTMoEForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"attention_heads": 12,
|
| 9 |
+
"batch_prioritized_routing": false,
|
| 10 |
+
"bos_token_id": 50257,
|
| 11 |
+
"classifier_dropout": 0.1,
|
| 12 |
+
"d_model": 768,
|
| 13 |
+
"embed_dropout": 0.0,
|
| 14 |
+
"eos_token_id": 50259,
|
| 15 |
+
"expert_capacity": null,
|
| 16 |
+
"ffn_dim": 3072,
|
| 17 |
+
"hidden_size": 768,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"max_position_embeddings": 2048,
|
| 20 |
+
"moe_eval_capacity_token_fraction": -1.0,
|
| 21 |
+
"moe_token_dropout": 0.2,
|
| 22 |
+
"no_scale_embedding": false,
|
| 23 |
+
"normalize_router_prob_before_dropping": false,
|
| 24 |
+
"num_experts": 512,
|
| 25 |
+
"num_heads": 12,
|
| 26 |
+
"num_layers": 12,
|
| 27 |
+
"output_router_logits": true,
|
| 28 |
+
"pad_token_id": 50258,
|
| 29 |
+
"resid_dropout": 0.1,
|
| 30 |
+
"router_bias": false,
|
| 31 |
+
"router_dtype": "float32",
|
| 32 |
+
"router_ignore_padding_tokens": true,
|
| 33 |
+
"second_expert_policy": "all",
|
| 34 |
+
"sparse_step": 2,
|
| 35 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.30.2",
|
| 38 |
+
"unk_token_id": 3,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 51200
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50257,
|
| 4 |
+
"eos_token_id": 50259,
|
| 5 |
+
"pad_token_id": 50258,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
pytorch_model-00001-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2be460f07d87505395c16ef8c6d57f92fda072adcf5784e806ff16704edbcd7d
|
| 3 |
+
size 9993386279
|
pytorch_model-00002-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e53b28ab5d7fdd32ce48abd534e86aec171f80358dafd4dbb9366ed82dd3da4
|
| 3 |
+
size 9995062183
|
pytorch_model-00003-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d701d892819c60ad29a4dfa7720e9e7b3648425630982aa595bef88d62d6b811
|
| 3 |
+
size 9995062247
|
pytorch_model-00004-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08d290dd56beab73a05c190661135d27b5d28adb620b78fa64689ccacb014361
|
| 3 |
+
size 9995062247
|
pytorch_model-00005-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86a3f7f6f67bbd020b4f515faef63ad23ff3d456295999234a6ce48773e6a5f8
|
| 3 |
+
size 9995062503
|
pytorch_model-00006-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03a0f896baea9fe91568161f9032eaa38cc79b16ecd8f241c39349627605eecc
|
| 3 |
+
size 8453823779
|
pytorch_model.bin.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|