Model Type |
| |
Additional Notes |
|
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 | 2025-02-15 |
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 | 4.44.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
GGUF16bit PromptRecovery Llama | 0 | 12 | 26 GB |
Llama13b 32K Illumeet Finetune | 0 | 13 | 26 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Llama13b 32K Illumeet Finetune | 32K / 26 GB | 13 | 0 |
...Maid V3 13B 32K 8.0bpw H8 EXL2 | 32K / 13.2 GB | 16 | 1 |
...Maid V3 13B 32K 6.0bpw H6 EXL2 | 32K / 10 GB | 13 | 1 |
WhiteRabbitNeo 13B V1 | 16K / 26 GB | 3168 | 411 |
CodeLlama 13B Python Fp16 | 16K / 26 GB | 2933 | 25 |
CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 2997 | 28 |
CodeLlama 13B Fp16 | 16K / 26 GB | 198 | 66 |
Codellama 13B Bnb 4bit | 16K / 7.2 GB | 123 | 2 |
...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 106 | 2 |
Airophin 13B Pntk 16K Fp16 | 16K / 26 GB | 1506 | 4 |
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