LLM Name | Pythia 1.4B Deduped Int4 Step36000 GPTQ Wikitext2 |
Repository ๐ค | https://huggingface.co/Xu-Ouyang/pythia-1.4b-deduped-int4-step36000-GPTQ-wikitext2 |
Model Size | 1.4b |
Required VRAM | 1 GB |
Updated | 2025-02-22 |
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 Step107000 GPTQ Wikitext2 | 2K / 1 GB | 76 | 0 |
... Int3 Step71000 GPTQ Wikitext2 | 2K / 0.9 GB | 78 | 0 |
...Int3 Step143000 GPTQ Wikitext2 | 2K / 0.9 GB | 78 | 0 |
...Int3 Step110000 GPTQ Wikitext2 | 2K / 0.9 GB | 78 | 0 |
...Int4 Step110000 GPTQ Wikitext2 | 2K / 1 GB | 78 | 0 |
...Int4 Step143000 GPTQ Wikitext2 | 2K / 1 GB | 78 | 0 |
... Int4 Step71000 GPTQ Wikitext2 | 2K / 1 GB | 77 | 0 |
...4B Deduped Int4 GPTQ Wikitext2 | 2K / 1.5 GB | 5 | 0 |
Pythia 1.4B Deduped 8K Base | 8K / 7.3 GB | 4 | 1 |
Pythia 1.4B Deduped 4K Base | 4K / 6.1 GB | 162 | 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