LLM Name | Tinyllama Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/tinyllama-bnb-4bit |
Model Size | 630.9m |
Required VRAM | 0.8 GB |
Updated | 2024-09-20 |
Maintainer | unsloth |
Model Type | llama |
Model Files | |
Supported Languages | en |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.37.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Smolphin Test1 | 0 | 0 | 2 GB |
QuantumQuill | 0 | 5 | 2 GB |
Cisco INAM 1.1B | 0 | 7 | 0 GB |
Valcal Q4 K M Guff | 0 | 24 | 0 GB |
...lama Bnb 4bit Clva Q4 K M Gguf | 0 | 24 | 0 GB |
Tinyllama Bnb 4bit Clva Gguf | 0 | 21 | 0 GB |
Tinyllama Gguf Q5 | 0 | 13 | 0 GB |
Tinyllama Gguf Q4 | 0 | 12 | 0 GB |
Tinyllama Gguf 16B | 0 | 11 | 2 GB |
Tinyllama Singlish | 0 | 5 | 2 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Tinyllama | 4K / 0.8 GB | 5 | 0 |
Merged 4bit Tiny Llama Gc2 | 4K / 0.8 GB | 5 | 0 |
Tinyllama Singlish GPT | 2K / 0.8 GB | 5 | 0 |
Jenna Tiny 2.0 | 2K / 0.8 GB | 6 | 0 |
Palmer 003 Turbo 2401 | 2K / 0.8 GB | 8 | 1 |
Palmer 003 Turbo | 2K / 0.8 GB | 6 | 1 |
V11Q | 2K / 0.8 GB | 5 | 0 |
MCQV3 Q | 2K / 0.8 GB | 5 | 0 |
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