Downloads · 30 days
4
1% of all-time downloads
noname-ai-v2-light
huskyhong/noname-ai-v2-light
noname-ai-v2-light is a text generation model from huskyhong. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
460
Public
Parameters
1.8B
3.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen
- Access
- Public
- Created
- Dec 11, 2023
- Updated
- Dec 11, 2023
- SHA
- 0fc7395d
Model card
From the Hugging Face model README
finetuned from qwen-1.8B-Chat
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
tokenizer = AutoTokenizer.from_pretrained("huskyhong/noname-ai-v2-light", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("huskyhong/noname-v2-light", device_map="auto", trust_remote_code=True).eval() # 采用gpu加载模型
# model = AutoModelForCausalLM.from_pretrained("huskyhong/noname-v2-light", device_map="cpu", trust_remote_code=True).float() # 采用cpu加载模型
model.generation_config = GenerationConfig.from_pretrained("huskyhong/noname-v2-light", trust_remote_code=True) # 可指定不同的生成长度、top_p等相关超参
prompt = "请帮我编写一个技能，技能效果如下：" + input("请输入技能效果：")
response, history = model.chat(tokenizer, prompt, history = [])
print(response)
prompt = "请帮我编写一张卡牌，卡牌效果如下：：" + input("请输入卡牌效果：")
response, history = model.chat(tokenizer, prompt, history = [])
print(response)
- Task
- Text Generation
- Library
- transformers
- Type
- qwen
- License
- apache-2.0
- Languages
- zh
- Created
- Dec 11, 2023
- Updated
- Dec 11, 2023