Model Card on HF 🤗: https://huggingface.co/casperhansen/aquila-2-7b-chat-awq
Aquila 2 7B Chat 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)
Aquila 2 7B Chat AWQ Parameters and Internals
| LLM Name | Aquila 2 7B Chat AWQ |
| Repository 🤗 | https://huggingface.co/casperhansen/aquila-2-7b-chat-awq |
| Model Size | 7b |
| Required VRAM | 5 GB |
| Updated | 2025-09-23 |
| Maintainer | casperhansen |
| Model Type | aquila |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | AquilaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 100008 |
| Torch Data Type | float16 |
Best Alternatives to Aquila 2 7B Chat AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| AquilaChat2 7B 16K | 16K / 29.2 GB | 25 | 9 |
| Aquila2 7B | 8K / 30.8 GB | 45 | 6 |
| AquilaChat2 7B | 2K / 29.2 GB | 9932 | 16 |
| Aquilachat 7B | 2K / 14.5 GB | 7 | 17 |
| Aquila 7B | 2K / 14.5 GB | 7 | 11 |
| Tiny Random Aquilachat | 0.1K / 0 GB | 102395 | 0 |
| Tiny Random Aquila2 | 0.1K / 0 GB | 102316 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than casperhansen/aquila-2-7b-chat-awq .
Rank the Aquila 2 7B Chat 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124