Model Card on HF 🤗: https://huggingface.co/WillHeld/via-llama
Via Llama 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)
Via Llama Parameters and Internals
| LLM Name | Via Llama |
| Repository 🤗 | https://huggingface.co/WillHeld/via-llama |
| Model Size | 9.6b |
| Required VRAM | 38.3 GB |
| Updated | 2025-02-22 |
| Maintainer | WillHeld |
| Model Files | |
| Model Architecture | AutoModel |
| Transformers Version | 4.38.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_0|> |
| Vocabulary Size | 128256 |
Best Alternatives to Via Llama
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama3 Via V0 | 0K / 38.3 GB | 16 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than WillHeld/via-llama .
Rank the Via Llama 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227