Model Card on HF 🤗: https://huggingface.co/casperhansen/yi-6b-awq
Yi 6B AWQ Benchmarks
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)
Yi 6B AWQ Parameters and Internals
| LLM Name | Yi 6B AWQ |
| Repository 🤗 | https://huggingface.co/casperhansen/yi-6b-awq |
| Model Size | 6b |
| Required VRAM | 3.9 GB |
| Updated | 2024-12-22 |
| Maintainer | casperhansen |
| Model Type | Yi |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | YiForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | YiTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | float16 |
Best Alternatives to Yi 6B AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yi 6B 200K AWQ | 195K / 3.9 GB | 59 | 2 |
| Dragon Yi 6B V0 AWQ | 4K / 3.9 GB | 29 | 2 |
| Yi 6B AWQ | 4K / 3.9 GB | 32 | 1 |
| ...o Claude Puffin 8.0bpw H8 EXL2 | 195K / 6.3 GB | 5 | 1 |
| ... Spicyboros 3.1 4.0bpw H6 EXL2 | 4K / 3.5 GB | 13 | 3 |
| ... Spicyboros 3.1 3.0bpw H6 EXL2 | 4K / 2.8 GB | 14 | 1 |
| Yi 6B 200K GPTQ | 195K / 3.9 GB | 66 | 2 |
| Yi 6B 200K Airo Claude Puffin | 195K / 12.1 GB | 8 | 1 |
| Dragon Yi 6B V0 | 4K / 3.7 GB | 60 | 60 |
| Yi 6B GPTQ | 4K / 3.9 GB | 92 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than casperhansen/yi-6b-awq .
Rank the Yi 6B AWQ 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217