| LLM Name | Pythia 2.8B Deduped Int3 Step143000 GPTQ Wikitext2 | 
| Repository ๐ค | https://huggingface.co/Xu-Ouyang/pythia-2.8b-deduped-int3-step143000-GPTQ-wikitext2 | 
| Model Size | 2.8b | 
| Required VRAM | 1.5 GB | 
| Updated | 2025-09-23 | 
| Maintainer | Xu-Ouyang | 
| Model Type | gpt_neox | 
| Model Files | |
| GPTQ Quantization | Yes | 
| Quantization Type | gptq | 
| Model Architecture | GPTNeoXForCausalLM | 
| Context Length | 2048 | 
| Model Max Length | 2048 | 
| Transformers Version | 4.41.2 | 
| Tokenizer Class | GPTNeoXTokenizer | 
| Vocabulary Size | 50304 | 
| Torch Data Type | float16 | 
| Best Alternatives | Context / RAM | Downloads | Likes | 
|---|---|---|---|
| ...Int3 Step107000 GPTQ Wikitext2 | 2K / 1.5 GB | 5 | 0 | 
| ...Int4 Step110000 GPTQ Wikitext2 | 2K / 1.8 GB | 6 | 0 | 
| ...Int4 Step143000 GPTQ Wikitext2 | 2K / 1.8 GB | 6 | 0 | 
| ... Int3 Step71000 GPTQ Wikitext2 | 2K / 1.5 GB | 5 | 0 | 
| ...Int3 Step110000 GPTQ Wikitext2 | 2K / 1.5 GB | 5 | 0 | 
| ... Int4 Step71000 GPTQ Wikitext2 | 2K / 1.8 GB | 5 | 0 | 
| Pythia 2.8B Deduped GPTQ | 2K / 1.8 GB | 6 | 0 | 
| Cassandra 2.8B | 4K / 1.7 GB | 6 | 5 | 
| Statichh Pythia 2.8B Sft Bf16 | 2K / 11.1 GB | 52 | 0 | 
| Pythia 2.8B Thai Base V1 | 2K / 5.9 GB | 5 | 2 | 
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