LLM Name | GPTQ Quantized 4bit Mcqa Llama Lora Model |
Repository ๐ค | https://huggingface.co/beam-searchers/GPTQ-quantized-4bit-mcqa-llama-lora-model |
Model Size | 2b |
Required VRAM | 5.8 GB |
Updated | 2025-06-09 |
Maintainer | beam-searchers |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Model Architecture | AutoModelForCausalLM |
Model Max Length | 8192 |
Is Biased | none |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|reserved_special_token_250|> |
PEFT Type | LORA |
LoRA Model | Yes |
PEFT Target Modules | o_proj|q_proj|v_proj|up_proj|gate_proj|k_proj|down_proj |
LoRA Alpha | 16 |
LoRA Dropout | 0 |
R Param | 16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Hellfire 2B | 0K / 0.3 GB | 3381 | 1 |
Gemma 1.1 QG V.2.0 | 0K / 5.1 GB | 8 | 0 |
Gemma2 Financial | 0K / 5.1 GB | 15 | 1 |
...Summarizer 2B It LORA Bnb 4bit | 0K / 0.1 GB | 15 | 1 |
Gemma 2B Hinglish LORA V1.0 | 0K / 5.1 GB | 17 | 0 |
Gemma 2 Baku 2B | 8K / 10.5 GB | 436 | 7 |
...emma 2B Lora Lbox Ljp Modified | 0K / 10 GB | 13 | 0 |
Gemma 2B Orca Mwp Lora V0.2 | 0K / 0.2 GB | 14 | 0 |
...hogpt Ft Qna Qchv 2021 Test Gr | 0K / 0.1 GB | 11 | 0 |
Quantized Mcqa Model | 0K / 5.8 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