Commit
•
bac1fa6
1
Parent(s):
56aa6c3
Upload LlamaForCausalLM
Browse files- config.json +13 -11
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,23 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/workspace/pretraining/local-models/training
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
|
|
|
| 6 |
"bos_token_id": 1,
|
| 7 |
"eos_token_id": 2,
|
| 8 |
"hidden_act": "silu",
|
| 9 |
-
"hidden_size":
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
-
"intermediate_size":
|
| 12 |
"max_position_embeddings": 1024,
|
| 13 |
-
"model_type": "
|
| 14 |
-
"num_attention_heads":
|
| 15 |
-
"num_hidden_layers":
|
| 16 |
-
"num_key_value_heads":
|
| 17 |
-
"
|
|
|
|
|
|
|
| 18 |
"rope_theta": 10000.0,
|
| 19 |
-
"
|
| 20 |
-
"tie_word_embeddings": true,
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.34.1",
|
| 23 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/workspace/new/pretraining/local-models/training//2024-02-10_22-40-13",
|
| 3 |
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
"max_position_embeddings": 1024,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 8,
|
| 16 |
+
"num_hidden_layers": 12,
|
| 17 |
+
"num_key_value_heads": 4,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
|
|
|
| 23 |
"torch_dtype": "float32",
|
| 24 |
"transformers_version": "4.34.1",
|
| 25 |
"use_cache": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5a8eede09cdf2a7b61b532e0ad1381d2a9469bc868455b3b2b050d11cf0228f
|
| 3 |
+
size 733541408
|