GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
745H1N
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
745H1N
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Fine-tuned only on 2,117 synthesized jfinqa-format QA pairs with worked-solution completions, generated from EDINET-Bench filings (structured summary/PL/BS/CF of Japanese securities reports). No jfinqa test data was used for training: all 104 EDINET codes appearing in the official jfinqa test set were excluded from the training pool (0 overlapping companies, 0 id collisions, 0 identical question texts - programmatically asserted).
q_proj, k_proj, v_proj, o_proj - 7,372,800 trainable params (0.24%)python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig base_id = "Qwen/Qwen2.5-3B-Instruct"adapter_id = "745H1N/ZERO-Kin1" # this repobnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.float16, bnb_4bit_use_double_quant=True)tok = AutoTokenizer.from_pretrained(base_id)model = PeftModel.from_pretrained( AutoModelForCausalLM.from_pretrained(base_id, quantization_config=bnb, device_map="auto"), adapter_id)model.eval() prompt = ( "以下の財務データ(表)と文章を読み、質問に答えてください。\n" "計算は正確に行い、最終的な答えのみを出力してください（説明や単位の補足は最小限）。\n\n" + pre_text + "\n[表]\n" + table + "\n" + post_text + "\n" + "[質問] " + question + "\n[答え] ")inputs = tok(prompt, return_tensors="pt", truncation=True, max_length=1280).to(model.device)out = model.generate(**inputs, max_new_tokens=160, do_sample=False, pad_token_id=tok.eos_token_id)text = tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)answer = text.strip().split("\n")[-1] # the final answer is the LAST lineThe model emits a short arithmetic working before the answer; consumers should take the last line (the answer is in the official jfinqa answer format: 1-decimal percentages, comma-grouped amounts, はい/いいえ・増収/減収 categoricals).
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig base_id = "Qwen/Qwen2.5-3B-Instruct"adapter_id = "745H1N/ZERO-Kin1" # this repobnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.float16, bnb_4bit_use_double_quant=True)tok = AutoTokenizer.from_pretrained(base_id)model = PeftModel.from_pretrained( AutoModelForCausalLM.from_pretrained(base_id, quantization_config=bnb, device_map="auto"), adapter_id)model.eval() prompt = ( "以下の財務データ(表)と文章を読み、質問に答えてください。\n" "計算は正確に行い、最終的な答えのみを出力してください（説明や単位の補足は最小限）。\n\n" + pre_text + "\n[表]\n" + table + "\n" + post_text + "\n" + "[質問] " + question + "\n[答え] ")inputs = tok(prompt, return_tensors="pt", truncation=True, max_length=1280).to(model.device)out = model.generate(**inputs, max_new_tokens=160, do_sample=False, pad_token_id=tok.eos_token_id)text = tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)answer = text.strip().split("\n")[-1] # the final answer is the LAST line