Downloads · 30 days
13
5% of all-time downloads
Ljy2004/mapfinben-qwen35-9b-merged-unified-v3
mapfinben-qwen35-9b-merged-unified-v3 is a machine learning model from Ljy2004. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Unified LoRA fine-tuned Qwen3.5-9B-Base for CCL26-Eval-MapFinBen (v3).
Downloads · 30 days
13
5% of all-time downloads
All-time downloads
258
Public
Parameters
9.4B
18.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors18.8 GB · 100%
From the Hugging Face model README
Unified LoRA fine-tuned Qwen3.5-9B-Base for CCL26-Eval-MapFinBen (v3).
from transformers import AutoModelForCausalLM, AutoTokenizer
model_path = "Ljy2004/mapfinben-qwen35-9b-merged-unified-v3"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_path, trust_remote_code=True, torch_dtype="auto", device_map="auto"
)
messages = [{"role": "user", "content": "YOUR_PROMPT"}]
text = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
Important: Use Qwen3.5 chat template with enable_thinking=False to match training and official evaluation.
MapFinBen benchmark: https://github.com/HgITSE/MapFinBen