LLM Name | EPFL TA Meister GPTQ 4bit |
Repository ๐ค | https://huggingface.co/PeterAM4/EPFL-TA-Meister-GPTQ-4bit |
Model Size | 2b |
Required VRAM | 5.8 GB |
Updated | 2025-06-09 |
Maintainer | PeterAM4 |
Model Type | llama |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Model Architecture | LlamaForCausalLM |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.41.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|end_of_text|> |
Vocabulary Size | 128256 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...etune 16bit Wiki 250 Ver2 GPTQ | 8K / 5.8 GB | 17 | 0 |
Llama 3 Teachtechai Gptq | 8K / 5.8 GB | 14 | 0 |
Mythalion Kimiko V2 GPTQ | 4K / 7.3 GB | 26 | 3 |
Stheno V2 Delta GPTQ | 4K / 7.3 GB | 18 | 3 |
...yn Education Corpus Qa V2 GPTQ | 4K / 7.3 GB | 36 | 3 |
Athena V4 GPTQ | 4K / 7.3 GB | 26 | 8 |
Athena V3 GPTQ | 4K / 7.3 GB | 10 | 10 |
Athena V2 GPTQ | 4K / 7.3 GB | 18 | 4 |
OpenOrca Stx GPTQ | 4K / 7.3 GB | 17 | 1 |
...T Lora Assamble Marcoroni GPTQ | 4K / 7.3 GB | 12 | 1 |
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