Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-3b-ins... Codegen Conversational Dataset:glaiveai/glaive-code-a... En Endpoints compatible Gguf Instruct Llama Pytorch Quantized Qwen2 Region:us Safetensors Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/yasserrmd/Coder-GRPO-3B
Coder GRPO 3B Benchmarks
MMLU Pro: 24.41
GPQA: 3.69
MUSR: 10.37
BBH: 22.91
IFEval: 62.08 vs 88 (so35)-29.5%
MATH Lvl 5: 32.02
LLME Score: 0.36461
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Coder GRPO 3B Parameters and Internals
| LLM Name | Coder GRPO 3B |
| Repository 🤗 | https://huggingface.co/yasserrmd/Coder-GRPO-3B |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.2 GB |
| Updated | 2025-03-12 |
| Maintainer | yasserrmd |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Generates Code | Yes |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Coder GRPO 3B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...2.5 Coder 3B Instruct Bnb 4bit | 32K / 2 GB | 6025 | 3 |
| Qwen3b Lora Finetune | 32K / 6.2 GB | 11 | 1 |
| Q2.5 CodeR1 3B | 32K / 6.2 GB | 226 | 1 |
| Qwen 2.5 3b Smarteaz 0.01a | 32K / 6.3 GB | 39 | 1 |
| Qwen2.5 Coder 3B Instruct | 32K / 6.2 GB | 80126 | 42 |
| Hammer2.1 3B | 32K / 6.2 GB | 5147 | 5 |
| Dria Agent A 3B | 32K / 6.2 GB | 232 | 51 |
| Qwen2.5 Coder 3B Instruct | 32K / 6.2 GB | 2658 | 3 |
| Arch Function 3B | 32K / 6.2 GB | 1301 | 111 |
| Qwen2.5 Coder 3B Instruct AWQ | 32K / 2.7 GB | 1018 | 4 |
Rank the Coder GRPO 3B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 44902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227