Autotrain compatible Conversational En Endpoints compatible Pretrained Qwen2 Region:us Safetensors Sharded Tensorflow
Qwen1.5 4B Benchmarks
ARC: 48.46-49.7%
HellaSwag: 71.58-24.9%
MMLU: 56.52-34.7%
TruthfulQA: 47.27-19.9%
WinoGrande: 66.22-24.3%
GSM8K: 52.24-43.2%
nn.n% — How the model compares to the GPT-4.
Qwen1.5 4B Parameters and Internals
| LLM Name | Qwen1.5 4B |
| Repository | Open on 🤗 |
| Model Size | 4b |
| Required VRAM | 7.9 GB |
| Updated | 2024-07-27 |
| 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 4B
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Qwen1.5 4B Chat | 0.3 | 32K / 7.9 GB | 15196 | 35 |
| Sailor 4B | 0.3 | 32K / 7.9 GB | 314 | 6 |
| Nusantara 4B Indo Chat | 0.3 | 32K / 7.9 GB | 325 | 1 |
| Sailor 4B Chat | 0.3 | 32K / 7.9 GB | 340 | 2 |
| Qwen1.5 Wukong 4B | 0.3 | 32K / 7.9 GB | 250 | 2 |
| Qwen 4B Flock 1719848483 | 0.3 | 32K / 7.9 GB | 26 | 0 |
| Reyna CoT 4B V0.1 | 0.3 | 32K / 7.9 GB | 301 | 5 |
| NOVA 3 1.5B | 0.3 | 32K / 14.3 GB | 34 | 0 |
| Blossom V5 4B | 0.3 | 32K / 7.9 GB | 311 | 2 |
| Qwen 4B Flock 1719855002 | 0.3 | 32K / 7.9 GB | 24 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-4B .
Rank the Qwen1.5 4B 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