Commit
•
5175553
1
Parent(s):
8403597
Upload NGMEForCausalLM
Browse files- config.json +30 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/glusterfs/dfs-gfs-dist/hallepat/rwkv-model",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"NGMEForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 0,
|
| 8 |
+
"ffn_dim": 512,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"model_type": "ngme",
|
| 15 |
+
"num_attention_heads": 6,
|
| 16 |
+
"num_hidden_layers": 8,
|
| 17 |
+
"num_key_value_heads": 6,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.31.0",
|
| 25 |
+
"unk_idx": 1,
|
| 26 |
+
"unk_token_id": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_flash_attn": false,
|
| 29 |
+
"vocab_size": 36484
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.31.0"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c769661761a4c94f3dc71037a310d3a741c2c8761b8da26377760bdd05ab47b
|
| 3 |
+
size 1111329042
|