Merged Model Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-coder-... Codegen Instruct Qwen/qwen2.5-coder-0.5b-instru... Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/someon98/qwen-CoMa-0.5b
Qwen CoMa 0.5B Benchmarks
MMLU Pro: 1.1
MUSR: 8.7
BBH: 2.13
IFEval: 22.77 vs 88 (so35)-74.1%
MATH Lvl 5: 0.45
LLME Score: 0.21649
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)
Qwen CoMa 0.5B Parameters and Internals
| LLM Name | Qwen CoMa 0.5B |
| Repository 🤗 | https://huggingface.co/someon98/qwen-CoMa-0.5b |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 0.5b |
| Required VRAM | 1.3 GB |
| Updated | 2025-09-08 |
| Maintainer | someon98 |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen CoMa 0.5B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 Coder 0.5B Instruct | 32K / 1 GB | 34495 | 50 |
| Qwen2.5 Coder 0.5B Instruct | 32K / 1 GB | 1967 | 4 |
| Qwen2.5 Coder 0.5B Instruct | 32K / 1 GB | 8 | 0 |
| Qwen2.5 Coder 0.5B Instruct | 32K / 1 GB | 7 | 0 |
| ...nstruct MIFT En Manywords 8000 | 32K / 2 GB | 8 | 0 |
| ...truct PIFT Enja Manywords 8000 | 32K / 2 GB | 8 | 0 |
| ...truct PIFT Enja Manywords 6000 | 32K / 2 GB | 8 | 0 |
| ...B Instruct BIFT Manywords 2000 | 32K / 2 GB | 6 | 0 |
| Hammer2.1 0.5B | 32K / 1 GB | 236 | 2 |
| ...nstruct MIFT Ja Manywords 4000 | 32K / 2 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than someon98/qwen-CoMa-0.5b .
Rank the Qwen CoMa 0.5B 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? 51191 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124