Model Card on HF 🤗: https://huggingface.co/chavinlo/vicuna2
Vicuna2 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)
Vicuna2 Parameters and Internals
| LLM Name | Vicuna2 |
| Repository 🤗 | https://huggingface.co/chavinlo/vicuna2 |
| Model Size | 13b |
| Required VRAM | 0 GB |
| Updated | 2025-02-05 |
| Maintainer | chavinlo |
| Model Type | llama |
| Model Files | |
| Model Architecture | LLaMAForCausalLM |
| Model Max Length | 1024 |
| Transformers Version | 4.27.0.dev0 |
| Tokenizer Class | LLaMATokenizer |
| Vocabulary Size | 32001 |
| Torch Data Type | float32 |
Best Alternatives to Vicuna2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llm Jp 13B V2.0 | 4K / 27.4 GB | 688 | 15 |
| Decapoda Research Llama 13B | 0K / 41 GB | 5 | 0 |
| LIMA 13B | 0K / 42 GB | 1247 | 1 |
| Alpaca 13B | 0K / 52.1 GB | 2347 | 108 |
| Llama 13B | 0K / 42 GB | 15 | 1 |
| Llama 13B | 0K / 42 GB | 9 | 3 |
| ... X Alpaca 13B Native 4bit 128g | 0K / 7.9 GB | 1498 | 735 |
| ... X Alpaca 13B Native 4bit 128g | 0K / 8.1 GB | 4 | 2 |
| Llama 13B 4bit Hf | 0K / 7 GB | 6 | 2 |
| Llama 13B 4bit Gr128 | 0K / 7.5 GB | 5 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than chavinlo/vicuna2 .
Rank the Vicuna2 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227