license, language, base_model, pipeline_tag, library_name, tags, model-index

license	language	base_model	pipeline_tag	library_name	tags	model-index
apache-2.0	en zh	Qwen/Qwen2.5-7B-Instruct	text-generation	transformers	text-generation-inference trl coder 7B	name results Viper-Coder-HybridMini-v1.3 task dataset metrics source type name text-generation Text Generation name type split args IFEval (0-Shot) wis-k/instruction-following-eval train num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 61.04 averaged accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FViper-Coder-HybridMini-v1.3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args BBH (3-Shot) SaylorTwift/bbh test num_few_shot 3 type value name acc_norm 33.67 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FViper-Coder-HybridMini-v1.3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args MATH Lvl 5 (4-Shot) lighteval/MATH-Hard test num_few_shot 4 type value name exact_match 46.3 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FViper-Coder-HybridMini-v1.3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args GPQA (0-shot) Idavidrein/gpqa train num_few_shot 0 type value name acc_norm 8.95 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FViper-Coder-HybridMini-v1.3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 15.61 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FViper-Coder-HybridMini-v1.3 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 37.24 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard#/?search=prithivMLmods%2FViper-Coder-HybridMini-v1.3 Open LLM Leaderboard

Viper-Coder-HybridMini-v1.3

Viper-Coder-HybridMini-v1.3 is based on the Qwen 2.5 7B modality architecture, designed to be the best for coding and reasoning tasks. It has been fine-tuned on a synthetic dataset leveraging the latest coding logits and CoT datasets, further optimizing its chain-of-thought (CoT) reasoning and logical problem-solving abilities. The model demonstrates significant improvements in context understanding, structured data processing, and long-context comprehension, making it ideal for complex coding tasks, instruction-following, and text generation.

Key Improvements

1. Best-in-Class Coding Proficiency: Enhanced understanding of programming languages, debugging, and code generation.
2. Fine-Tuned Instruction Following: Optimized for precise responses, structured outputs (e.g., JSON, YAML), and extended text generation (8K+ tokens).
3. Advanced Logical & Mathematical Reasoning: Improved multi-step problem-solving and theorem proving.
4. Long-Context Mastery: Handles up to 128K tokens with an output capability of 8K tokens per response.
5. Multilingual Code Support: Excels in Python, JavaScript, C++, Java, SQL, and other major programming languages, with documentation in 29+ languages.

Quickstart with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Viper-Coder-HybridMini-v1.3"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Write a Python function to merge two sorted lists."
messages = [
    {"role": "system", "content": "You are an advanced AI assistant with expert-level coding and reasoning abilities."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)

Intended Use

• Elite Coding & Debugging: Best-in-class model for writing, analyzing, and optimizing code.
• Complex Algorithmic Reasoning: Solves intricate logic problems and algorithm-based challenges.
• Scientific & Mathematical Computation: Advanced support for formulas, equations, and theorem verification.
• Structured Data Processing: Seamlessly handles JSON, XML, SQL, and data pipeline automation.
• Multilingual Programming Support: Proficient in Python, JavaScript, C++, Java, Go, and more.
• Extended Technical Content Generation: Ideal for writing documentation, research papers, and technical blogs.

Limitations

1. Moderate Computational Demand: Requires GPUs/TPUs for smooth inference due to 7B parameters, but more lightweight than larger models.
2. Language-Specific Variability: Performance may vary across different programming languages.
3. Possible Error Propagation: Extended text outputs might introduce logical inconsistencies.
4. Limited Real-World Awareness: The model does not have access to real-time internet updates.
5. Prompt Sensitivity: Performance depends on how well the prompt is structured.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here! Summarized results can be found here!

Metric	Value (%)
Average	33.80
IFEval (0-Shot)	61.04
BBH (3-Shot)	33.67
MATH Lvl 5 (4-Shot)	46.30
GPQA (0-shot)	8.95
MuSR (0-shot)	15.61
MMLU-PRO (5-shot)	37.24