LLM Name | Nethena 13B 4bpw H8 EXL2 |
Repository | Open on ๐ค |
Model Size | 13b |
Required VRAM | 6.8 GB |
Updated | 2024-07-27 |
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 |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...Maid V3 13B 32K 6.0bpw H6 EXL2 | 0.2 | 32K / 10 GB | 7 | 1 |
...Maid V3 13B 32K 8.0bpw H8 EXL2 | 0.2 | 32K / 13.2 GB | 6 | 1 |
WhiteRabbitNeo 13B V1 | 0.3 | 16K / 26 GB | 2238 | 372 |
CodeLlama 13B Python Fp16 | 0.2 | 16K / 26 GB | 1914 | 25 |
CodeLlama 13B Instruct Fp16 | 0.2 | 16K / 26 GB | 1927 | 29 |
Codellama 13B Bnb 4bit | 0.2 | 16K / 7.2 GB | 77 | 1 |
CodeLlama 13B Fp16 | 0.2 | 16K / 26 GB | 28 | 66 |
...Llama 13B Instruct Hf 4bit MLX | 0.2 | 16K / 7.8 GB | 9 | 2 |
...13B Instruct Nf4 Fp16 Upscaled | 0.2 | 16K / 26 GB | 572 | 0 |
Trinity 13B | 0.2 | 16K / 26 GB | 7 | 15 |
๐ 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! ๐