Downloads · 30 days
1
2% of all-time downloads
sssssungjae/Qwen2.5-7B-instruct-finance-model_stock_v5
Qwen2.5-7B-instruct-finance-model_stock_v5 is a machine learning model from sssssungjae. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Qwen2.5-7B-instruct-finance-modelstockv5 is a merge of the following models using LazyMergekit:
Downloads · 30 days
1
2% of all-time downloads
All-time downloads
61
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-finance-model_stock_v5 is a merge of the following models using LazyMergekit:
merge_method: model_stock
base_model: Qwen/Qwen2.5-7B
models:
- model: AnonymousLLMer/krx-qwen2.5-v1206-1
- model: sssssungjae/qwen2_5-7b-instruct-finance-full-final-15_15
- model: aiqwe/FinShibainu
parameters:
filter_wise: false
dtype: bfloat16
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "sssssungjae/Qwen2.5-7B-instruct-finance-model_stock_v5"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])