deepseek-math-7b-3epoch-678k-fullft/README.md

language, license, library_name, base_model, tags, datasets, metrics, model-index, pipeline_tag, inference

language	license	library_name	base_model	tags	datasets	metrics	model-index	pipeline_tag	inference
en	apache-2.0	transformers	deepseek-ai/deepseek-math-7b-base	mathematics math reasoning deepseek fine-tuned llama causal-lm competition-math gsm8k numinamath metamath aime amc olympiad	AI-MO/NuminaMath-CoT meta-math/MetaMathQA HuggingFaceH4/MATH-Train	accuracy perplexity	name results deepseek-math-7b-3epoch-678k-fullft task dataset metrics type name text-generation Mathematical Reasoning type name gsm8k GSM8K type value accuracy 82.0	text-generation	true

🚀 DeepSeek Math 7B - Full Fine-tune

Model ID: sid172002/deepseek-math-7b-3epoch-678k-fullft

Fully fine-tuned DeepSeek Math 7B on 678K high-quality math problems. +17.8% improvement over base model on GSM8K (64.2% → 82.0%).

📊 Quick Stats

Metric	Value
Parameters	7 Billion
Training Steps	63,609
Epochs	3.0
Dataset Size	678,494 samples
GSM8K Score	82.0%
Training Loss	0.6394
Eval Loss	0.6411

🏆 Benchmarks

Benchmark	Score	Base	Improvement
GSM8K	82.0%	64.2%	+17.8%
MathBench	92.0%	~70%	+22%
MMLU	Pending	-	Leaderboard Eval
MATH	TBD	33.2%	In Progress

💻 Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "sid172002/deepseek-math-7b-3epoch-678k-fullft",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "sid172002/deepseek-math-7b-3epoch-678k-fullft",
    trust_remote_code=True
)

# Solve math problem
problem = "What is 2x + 5 = 13?"
prompt = f"Solve step by step:\n\n{problem}\n\nSolution:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))