Upload LlamaForCausalLM
Browse files- config.json +4 -5
- generation_config.json +0 -1
- model.safetensors +2 -2
config.json
CHANGED
@@ -8,15 +8,14 @@
|
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "silu",
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
"max_position_embeddings": 4096,
|
15 |
"model_type": "llama",
|
16 |
-
"num_attention_heads":
|
17 |
"num_hidden_layers": 2,
|
18 |
-
"num_key_value_heads":
|
19 |
-
"pad_token_id": 0,
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-05,
|
22 |
"rope_scaling": null,
|
|
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "silu",
|
11 |
+
"hidden_size": 64,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 172,
|
14 |
"max_position_embeddings": 4096,
|
15 |
"model_type": "llama",
|
16 |
+
"num_attention_heads": 4,
|
17 |
"num_hidden_layers": 2,
|
18 |
+
"num_key_value_heads": 2,
|
|
|
19 |
"pretraining_tp": 1,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"rope_scaling": null,
|
generation_config.json
CHANGED
@@ -2,6 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"pad_token_id": 0,
|
6 |
"transformers_version": "4.39.0.dev0"
|
7 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
|
|
5 |
"transformers_version": "4.39.0.dev0"
|
6 |
}
|
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 sha256:962b91a746474291b571c632328128e861e12bf533462b6958105359d37c5e65
|
3 |
+
size 8376080
|