LLM Name | Llama 2 13B Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/llama-2-13b-bnb-4bit |
Model Size | 13b |
Required VRAM | 7.2 GB |
Updated | 2024-09-08 |
Maintainer | unsloth |
Model Type | llama |
Model Files | |
Supported Languages | en |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.37.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
GGUF16bit PromptRecovery Llama | 0 | 39 | 26 GB |
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 | 2 | 1 |
WhiteRabbitNeo 13B V1 | 16K / 26 GB | 1436 | 379 |
CodeLlama 13B Python Fp16 | 16K / 26 GB | 1427 | 25 |
CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 1436 | 29 |
Codellama 13B Bnb 4bit | 16K / 7.2 GB | 106 | 1 |
...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 11 | 2 |
CodeLlama 13B Fp16 | 16K / 26 GB | 19 | 66 |
...13B Instruct Nf4 Fp16 Upscaled | 16K / 26 GB | 372 | 0 |
WhiteRabbitNeo 13B V1 4bit Mlx | 16K / 7.8 GB | 2 | 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