Upload Qwen2ForCausalLM
Browse files- README.md +4 -19
- config.json +29 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
README.md
CHANGED
@@ -1,28 +1,13 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
language:
|
4 |
- zh
|
5 |
-
|
6 |
tags:
|
7 |
- not-for-all-audiences
|
|
|
8 |
---
|
9 |
|
10 |
-
数据来源自[h-corpus-2023](https://huggingface.co/
|
11 |
模型来源自[Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
|
12 |
|
13 |
-
|
14 |
-
|
15 |
-
```
|
16 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
17 |
-
|
18 |
-
repo_id = 'Monor/Qwen1.5-0.5B-h-world'
|
19 |
-
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
|
20 |
-
model = AutoModelForCausalLM.from_pretrained(repo_id, device_map="auto", trust_remote_code=True).eval()
|
21 |
-
|
22 |
-
inputs = tokenizer('小青突然来到了我的房间', return_tensors='pt')
|
23 |
-
inputs = inputs.to(model.device)
|
24 |
-
pred = model.generate(**inputs, max_new_tokens=32, num_beams=4, do_sample=True)
|
25 |
-
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
|
26 |
-
|
27 |
-
输出:小青突然来到了我的房间,吓了我一跳。她见我睡着了,就脱了衣服钻进了被窝里,然后搂着我睡着了。
|
28 |
-
```
|
|
|
1 |
---
|
|
|
2 |
language:
|
3 |
- zh
|
4 |
+
license: apache-2.0
|
5 |
tags:
|
6 |
- not-for-all-audiences
|
7 |
+
pipeline_tag: text-generation
|
8 |
---
|
9 |
|
10 |
+
数据来源自[h-corpus-2023](https://huggingface.co/a686d380/h-corpus-2023)
|
11 |
模型来源自[Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
|
12 |
|
13 |
+
训练中(30%)...请等待更新
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "checkpoints",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
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": "float32",
|
24 |
+
"transformers_version": "4.38.2",
|
25 |
+
"use_cache": false,
|
26 |
+
"use_dynamic_ntk": true,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 151936
|
29 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"eos_token_id": 151643,
|
4 |
+
"max_new_tokens": 2048,
|
5 |
+
"transformers_version": "4.38.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31d2d20652659003f74189e4b88727843129966783c090008b543aa4e1e756fc
|
3 |
+
size 1855983640
|