Pythia 12B Deduped Int4 Step107000 GPTQ Wikitext2 by Xu-Ouyang

 ยป  All LLMs  ยป  Xu-Ouyang  ยป  Pythia 12B Deduped Int4 Step107000 GPTQ Wikitext2   URL Share it on

  Arxiv:1910.09700   4-bit   Autotrain compatible   Endpoints compatible   Gpt neox   Gptq   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Pythia 12B Deduped Int4 Step107000 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").
๐ŸŒŸ Advertise your project ๐Ÿš€

Pythia 12B Deduped Int4 Step107000 GPTQ Wikitext2 Parameters and Internals

LLM NamePythia 12B Deduped Int4 Step107000 GPTQ Wikitext2
Repository ๐Ÿค—https://huggingface.co/Xu-Ouyang/pythia-12b-deduped-int4-step107000-GPTQ-wikitext2 
Model Size12b
Required VRAM6.9 GB
Updated2025-06-11
MaintainerXu-Ouyang
Model Typegpt_neox
Model Files  5.0 GB: 1-of-2   1.9 GB: 2-of-2
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureGPTNeoXForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.41.2
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50688
Torch Data Typefloat16
Pythia 12B Deduped Int4 Step107000 GPTQ Wikitext2 (Xu-Ouyang/pythia-12b-deduped-int4-step107000-GPTQ-wikitext2)

Best Alternatives to Pythia 12B Deduped Int4 Step107000 GPTQ Wikitext2

Best Alternatives
Context / RAM
Downloads
Likes
... Int4 Step36000 GPTQ Wikitext22K / 6.9 GB320
... Int3 Step71000 GPTQ Wikitext22K / 5.5 GB130
Merlyn Education Safety GPTQ2K / 6.9 GB253
Dolly V2 12B Sharded 8bit2K / 12.4 GB194
Dolly V2 12B2K / 23.8 GB28681954
Pythia 12B2K / 23.8 GB38722137
...sst Sft 4 Pythia 12B Epoch 3.52K / 23.8 GB4804367
Oasst Sft 1 Pythia 12B2K / 23.8 GB2035277
Pythia 12B Deduped2K / 23.8 GB835851
Pythia 12B Sft V8 7K Steps2K / 23.8 GB117621
Note: green Score (e.g. "73.2") means that the model is better than Xu-Ouyang/pythia-12b-deduped-int4-step107000-GPTQ-wikitext2.

Rank the Pythia 12B Deduped Int4 Step107000 GPTQ Wikitext2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 48079 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124