Model Type |
| |||
Input Output |
|
LLM Name | Universitytehran PersianMind V1.0 Bnb 4bit Smashed |
Repository ๐ค | https://huggingface.co/PrunaAI/universitytehran-PersianMind-v1.0-bnb-4bit-smashed |
Base Model(s) | |
Model Size | 3.7b |
Required VRAM | 4.3 GB |
Updated | 2025-01-17 |
Maintainer | PrunaAI |
Model Type | llama |
Model Files | |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.40.0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | [PAD] |
Vocabulary Size | 41510 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Tenebra PreAlpha 128g 3BIT | 2K / 13.5 GB | 17 | 0 |
Llm Jp 3 3.7B Instruct | 4K / 7.6 GB | 56177 | 9 |
Llm Jp 3 3.7B | 4K / 7.6 GB | 1426 | 8 |
...3 3.7B Instruct EZO Humanities | 4K / 7.6 GB | 173 | 4 |
Llm Jp 3 3.7B Instruct | 4K / 7.6 GB | 24 | 0 |
Cpt St Vicuna V1.3 3.7B Ppl | 2K / 7.4 GB | 28 | 5 |
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