Model Type |
| ||||||
Use Cases |
|
LLM Name | Trinity 13B 5.0bpw H6 EXL2 |
Repository ๐ค | https://huggingface.co/LoneStriker/Trinity-13B-5.0bpw-h6-exl2 |
Model Size | 13b |
Required VRAM | 8.4 GB |
Updated | 2024-12-21 |
Maintainer | LoneStriker |
Model Type | llama |
Model Files | |
Quantization Type | fp16|exl2 |
Generates Code | Yes |
Model Architecture | LlamaForCausalLM |
License | llama2 |
Context Length | 16384 |
Model Max Length | 16384 |
Transformers Version | 4.36.2 |
Tokenizer Class | CodeLlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 32016 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
WhiteRabbitNeo 13B V1 | 16K / 26 GB | 1817 | 404 |
CodeLlama 13B Python Fp16 | 16K / 26 GB | 1547 | 25 |
CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 2046 | 29 |
Codellama 13B Bnb 4bit | 16K / 7.2 GB | 122 | 1 |
CodeLlama 13B Fp16 | 16K / 26 GB | 24 | 66 |
...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 80 | 2 |
...13B Instruct Nf4 Fp16 Upscaled | 16K / 26 GB | 481 | 0 |
Trinity 13B | 16K / 26 GB | 22 | 15 |
Trinity 13B 6.0bpw H6 EXL2 | 16K / 10 GB | 9 | 2 |
Trinity 13B 3.0bpw H6 EXL2 | 16K / 5.2 GB | 10 | 1 |
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