| LLM Name | Pythia 1.4B Deduped Int3 Step110000 GPTQ Wikitext2 |
| Repository ๐ค | https://huggingface.co/Xu-Ouyang/pythia-1.4b-deduped-int3-step110000-GPTQ-wikitext2 |
| Model Size | 1.4b |
| Required VRAM | 0.9 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 |
|---|---|---|---|
| ... Int4 Step36000 GPTQ Wikitext2 | 2K / 1 GB | 6 | 0 |
| ...Int4 Step107000 GPTQ Wikitext2 | 2K / 1 GB | 6 | 0 |
| ...Int3 Step143000 GPTQ Wikitext2 | 2K / 0.9 GB | 6 | 0 |
| ... Int3 Step71000 GPTQ Wikitext2 | 2K / 0.9 GB | 5 | 0 |
| ... Int4 Step71000 GPTQ Wikitext2 | 2K / 1 GB | 6 | 0 |
| ...Int4 Step110000 GPTQ Wikitext2 | 2K / 1 GB | 5 | 0 |
| ...Int4 Step143000 GPTQ Wikitext2 | 2K / 1 GB | 5 | 0 |
| ...4B Deduped Int4 GPTQ Wikitext2 | 2K / 1.5 GB | 6 | 0 |
| Pythia 1.4B Deduped 8K Base | 8K / 7.3 GB | 6 | 1 |
| Pythia 1.4B Deduped 4K Base | 4K / 6.1 GB | 7 | 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