You can deploy this model and start earning money today!

sll0107/
Qwen3-8B-finance-v2

Name: Qwen3-8B-finance-v2
Availability: InStock

text-generation-inference

endpoints_compatible

Views

No views yet

Qwen3-8B Financial

A Qwen3-8B model fine-tuned for multilingual financial text understanding (question answering, multiple-choice, sentiment, topic classification, summarization).

Usage

The model answers directly without a system prompt. Feed the query verbatim (no chat wrapper / no system message). Greedy decoding (temperature 0) is recommended. Generation stops on <|im_end|>.

python

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("REPO_ID")
model = AutoModelForCausalLM.from_pretrained("REPO_ID", torch_dtype="bfloat16").cuda()
ids = tok(query, return_tensors="pt").input_ids.cuda()
out = model.generate(ids, max_new_tokens=300, do_sample=False)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

License

Apache-2.0, inherited from the base model (Qwen/Qwen3-8B).

sll0107/Qwen3-8B-finance-v2

Qwen3-8B Financial

Usage

License

sll0107/
Qwen3-8B-finance-v2