Upload Qwen2ForCausalLM (#1)
Browse files- Upload Qwen2ForCausalLM (54ebc4ea22c7bfd4dcf631435c824d7b26c7db8f)
- config.json +28 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 2816,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 21,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"num_key_value_heads": 16,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": 32768,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.40.1",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 151936
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"top_p": 0.8,
|
11 |
+
"transformers_version": "4.40.1"
|
12 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4e5f02a0df6bdeea743eb18bab9227c2a3ea56bbd31b247b2600a55a27a80bf
|
3 |
+
size 1239173352
|