Model Type |
| |||
Input Output |
|
LLM Name | Tinyllama Chat Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit |
Model Size | 630.9m |
Required VRAM | 0.8 GB |
Updated | 2024-12-21 |
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 | 4.44.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Tinyllama Coder Py V13 | 0 | 518 | 0 GB |
Tinyllama Coder Py V12 | 0 | 487 | 0 GB |
Tinyllama Coder Py 4bit V3 | 0 | 84 | 1 GB |
Tinyllama Coder Py 4bit V10 | 0 | 91 | 0 GB |
Tinyllama Coder Py V14 | 0 | 20 | 2 GB |
Tinyllama Coder Py 4bit V4 | 0 | 21 | 1 GB |
TinyLlama QuantumQuill Chat | 0 | 21 | 2 GB |
...a QuantumQuill Chat 08 05 24 2 | 0 | 18 | 2 GB |
...icipal Prediction Merged Model | 0 | 37 | 2 GB |
TinyLlama Indo Chat V.01 | 0 | 8 | 2 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Tinyllama | 4K / 0.8 GB | 25 | 0 |
Merged 4bit Tiny Llama Gc2 | 4K / 0.8 GB | 13 | 0 |
Tinyllama Singlish GPT | 2K / 0.8 GB | 11 | 0 |
Tinyllama Bnb 4bit | 2K / 0.8 GB | 4899 | 9 |
Jenna Tiny 2.0 | 2K / 0.8 GB | 11 | 0 |
Palmer 003 Turbo 2401 | 2K / 0.8 GB | 16 | 1 |
Palmer 003 Turbo | 2K / 0.8 GB | 19 | 1 |
V11Q | 2K / 0.8 GB | 9 | 0 |
MCQV3 Q | 2K / 0.8 GB | 9 | 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