Nethena 13B 4bpw H8 EXL2 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)
Nethena 13B 4bpw H8 EXL2 Parameters and Internals
| LLM Name | Nethena 13B 4bpw H8 EXL2 |
| Repository 🤗 | https://huggingface.co/Kooten/Nethena-13B-4bpw-h8-exl2 |
| Model Size | 13b |
| Required VRAM | 6.8 GB |
| Updated | 2024-10-18 |
| Maintainer | Kooten |
| Model Type | llama |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Nethena 13B 4bpw H8 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Maid V3 13B 32K 6.0bpw H6 EXL2 | 32K / 10 GB | 3 | 1 |
| ...Maid V3 13B 32K 8.0bpw H8 EXL2 | 32K / 13.2 GB | 1 | 1 |
| WhiteRabbitNeo 13B V1 | 16K / 26 GB | 1906 | 388 |
| CodeLlama 13B Python Fp16 | 16K / 26 GB | 1244 | 25 |
| CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 1791 | 29 |
| Codellama 13B Bnb 4bit | 16K / 7.2 GB | 158 | 1 |
| CodeLlama 13B Fp16 | 16K / 26 GB | 19 | 66 |
| ...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 26 | 2 |
| WhiteRabbitNeo 13B V1 4bit Mlx | 16K / 7.8 GB | 6 | 1 |
| Trinity 13B | 16K / 26 GB | 8 | 15 |
Note: green Score (e.g. "73.2") means that the model is better than Kooten/Nethena-13B-4bpw-h8-exl2 .
Rank the Nethena 13B 4bpw H8 EXL2 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803