Qwen1.5 0.5B Benchmarks
ARC: 31.48-67.3%
HellaSwag: 49.05-48.5%
MMLU: 39.35-54.5%
TruthfulQA: 38.3-35.1%
WinoGrande: 57.22-34.6%
GSM8K: 16.3-82.3%
nn.n% — How the model compares to the GPT-4.
Qwen1.5 0.5B Parameters and Internals
| LLM Name | Qwen1.5 0.5B |
| Repository | Open on 🤗 |
| Model Size | 0.5b |
| Required VRAM | 1.2 GB |
| Updated | 2024-07-26 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen1.5 0.5B
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Qwen2 0.5B | 0.4 | 128K / 1 GB | 129555 | 59 |
| Qwen2 0.5B | 0.3 | 128K / 1 GB | 1156 | 1 |
| Qwen2 Wukong 0.5B | 0.3 | 128K / 1.3 GB | 144 | 6 |
| Dolphin 2.9.3 Qwen2 0.5B | 0.3 | 128K / 1 GB | 538 | 3 |
| Qwen2 0.5B Fncl 2 | 0.3 | 128K / 1 GB | 216 | 0 |
| Qwen2 0.5B Fncl | 0.3 | 128K / 1 GB | 87 | 1 |
| Qwen2 0.5B Tldr Sft | 0.3 | 128K / 2 GB | 46 | 0 |
| Oneirogen 0.5B | 0.3 | 128K / 1 GB | 96 | 1 |
| D Qwen2 0.5B | 0.3 | 128K / 1 GB | 59 | 5 |
| LawToken 0.5B A2 | 0.3 | 128K / 2 GB | 65 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-0.5B .
Rank the Qwen1.5 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501