LLM Name | TaraV1 M16B |
Repository ๐ค | https://huggingface.co/Gragroo/taraV1-M16B |
Base Model(s) | |
Model Size | 3b |
Required VRAM | 6.5 GB |
Updated | 2025-01-19 |
Maintainer | Gragroo |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.44.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|finetune_right_pad_id|> |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Llama 3.2 3B Instruct 4bit | 128K / 1.8 GB | 940049 | 24 |
Llama 3.2 3B Instruct Bnb 4bit | 128K / 2.2 GB | 219458 | 15 |
Orca Mini V9 0 3B Instruct | 128K / 6.5 GB | 59 | 5 |
Llama32 3B En Emo V2 | 128K / 2.2 GB | 145 | 1 |
Komodo Llama 3.2 3B V2 Fp16 | 128K / 6.5 GB | 247 | 5 |
...r Mini Exp 1221 3B Instruct V2 | 128K / 6.5 GB | 21 | 0 |
...ator Mini Exp 1222 3B Instruct | 128K / 6.5 GB | 15 | 0 |
Gladiator Mini Exp 1211 3B | 128K / 6.5 GB | 6 | 0 |
Llama 3.2 3B Overthinker | 128K / 6.5 GB | 143 | 19 |
...ator Mini Exp 1221 3B Instruct | 128K / 6.5 GB | 14 | 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