4bit Autotrain compatible Conversational Dataset:qingy2024/qwq-longcot-... En Endpoints compatible Quantized Qwen2 Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/qingy2024/QwQ-14B-Math-v0.2
QwQ 14B Math V0.2 Benchmarks
MMLU Pro: 42.22
GPQA: 1.68
MUSR: 8.6
BBH: 39.1
IFEval: 33.91 vs 88 (so35)-61.5%
MATH Lvl 5: 19.03
LLME Score: 0.33452
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)
QwQ 14B Math V0.2 Parameters and Internals
| LLM Name | QwQ 14B Math V0.2 |
| Repository 🤗 | https://huggingface.co/qingy2024/QwQ-14B-Math-v0.2 |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 29.7 GB |
| Updated | 2024-12-31 |
| Maintainer | qingy2024 |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to QwQ 14B Math V0.2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...B Instruct 1M Unsloth Bnb 4bit | 986K / 14.3 GB | 372 | 2 |
| Qwen2.5 14B Instruct 1M 8bit | 986K / 15.7 GB | 342 | 2 |
| ...till Qwen 14B Unsloth Bnb 4bit | 128K / 13.9 GB | 15187 | 15 |
| ...k R1 Distill Qwen 14B Bnb 4bit | 128K / 9.9 GB | 3899 | 3 |
| Qwen Carpmuscle V0.3 | 128K / 29.7 GB | 5 | 0 |
| ...1 Distill Qwen 14B EXL2 8.0bpw | 128K / 14.7 GB | 216 | 2 |
| Qwen2.5 14B Bnb 4bit | 128K / 9.9 GB | 6780 | 5 |
| UwU 14B Math V0.2 | 128K / 29.7 GB | 198 | 18 |
| ...antha2.0 Qwen2.5 14B Ita 16bit | 128K / 29.7 GB | 2736 | 0 |
| ...ha2.0 Qwen2.5 14B Ita V2 16bit | 128K / 29.7 GB | 2515 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than qingy2024/QwQ-14B-Math-v0.2 .
Rank the QwQ 14B Math V0.2 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? 42935 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227