Arxiv:1910.09700 4-bit Autotrain compatible Endpoints compatible Gpt neox Gptq Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Xu-Ouyang/pythia-410m-deduped-int4-step110000-GPTQ-wikitext2
Pythia 410M Deduped Int4 Step110000 GPTQ Wikitext2 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Pythia 410M Deduped Int4 Step110000 GPTQ Wikitext2 Parameters and Internals
| LLM Name | Pythia 410M Deduped Int4 Step110000 GPTQ Wikitext2 |
| Repository 🤗 | https://huggingface.co/Xu-Ouyang/pythia-410m-deduped-int4-step110000-GPTQ-wikitext2 |
| Model Size | 410m |
| Required VRAM | 0.4 GB |
| Updated | 2025-06-09 |
| 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 to Pythia 410M Deduped Int4 Step110000 GPTQ Wikitext2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... Int3 Step71000 GPTQ Wikitext2 | 2K / 0.3 GB | 14 | 0 |
| ...thia 410M Cell Type Prediction | 4K / 0 GB | 609 | 6 |
| Pythia 410M | 2K / 0.9 GB | 153566 | 31 |
| Pythia 410M Sft Full | 2K / 0.8 GB | 24 | 0 |
| Pythia 410M Deduped SimPOW 0 | 2K / 0.8 GB | 12 | 0 |
| Pythia 410M Orpo | 2K / 1.6 GB | 9 | 0 |
| Healix 410M | 2K / 1.6 GB | 170 | 0 |
| Pythia 410M Ludii Sft | 2K / 1.6 GB | 10 | 0 |
| ...7 Kl 01 Steps 12000 Rlhf Model | 2K / 1.6 GB | 15 | 0 |
| Pythia 410M Deduped | 2K / 0.9 GB | 27784 | 20 |
Note: green Score (e.g. "73.2") means that the model is better than Xu-Ouyang/pythia-410m-deduped-int4-step110000-GPTQ-wikitext2 .
Rank the Pythia 410M Deduped Int4 Step110000 GPTQ Wikitext2 Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 48023 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124