Downloads · 30 days
15
4% of all-time downloads
gxinxing/qwen-trader-cn-merged
qwen-trader-cn-merged is a text generation model from gxinxing. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Qwen2.5-7B-Instruct 中文金融/交易微调版(全参微调后合并权重,可直接推理)。
Downloads · 30 days
15
4% of all-time downloads
All-time downloads
375
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.2 GB · 100%
From the Hugging Face model README
Qwen2.5-7B-Instruct 中文金融/交易微调版(全参微调后合并权重,可直接推理)。
Qwen2ForCausalLM(基础模型 Qwen/Qwen2.5-7B-Instruct)model.safetensors,约 15.2GB)面向中文金融/交易场景的文本生成模型,可用于行情分析、交易策略问答、财经信息解读等(本仓库为学术/工程备份用途,不构成投资建议)。
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "gxinxing/qwen-trader-cn-merged"
model = AutoModelForCausalLM.from_pretrained(
model_id, torch_dtype=torch.float16, device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_id)
prompt = "请分析今天的A股大盘走势"
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
gxinxing/qwen-trader-mergedgxinxing/qwen-trader-cn-lora、gxinxing/qwen-trader-lora