Downloads · 30 days
0
Cbgcbg/qwen3-1.7b-math-sft-stage1-20250723_111953
qwen3-1.7b-math-sft-stage1-20250723_111953 is a text generation model from Cbgcbg. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Stage 1 SFT model trained following "A Practical Two-Stage Recipe for Mathematical LLMs" paper.
Downloads · 30 days
0
Access
Public
Updated Jul 23, 2025
Repo size
433 MB
Likes
0
Public
Click a slice to open those files.
.safetensors419 MB · 69%
From the Hugging Face model README
Stage 1 SFT model trained following "A Practical Two-Stage Recipe for Mathematical LLMs" paper.
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name="Cbgcbg/qwen3-1.7b-math-sft-stage1-20250723_111953",
max_seq_length=8192,
dtype=None,
load_in_4bit=True,
)
# Example
messages = [
{"role": "system", "content": "Please reason step by step, and put your final answer within \boxed{}."},
{"role": "user", "content": "What is 2+2?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
outputs = model.generate(input_ids=inputs, max_new_tokens=256)
Based on the methodology from:
A Practical Two-Stage Recipe for Mathematical LLMs:
Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning
This is Stage 1 - focused on maximizing accuracy. Stage 2 (GRPO) will optimize for token efficiency.