Ypotryll 22B Gptq is an open-source language model by chargoddard. Features: 22b LLM, VRAM: 12GB, Context: 4K, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.08.
Ypotryll 22B Gptq Parameters and Internals
Model Type instruction-following, roleplay, chat
Additional Notes Good for creative scenarios; a bit on the simpler side in logic.
Training Details
Data Sources: jondurbin/airoboros-gpt4-1.4.1, ehartford/wizard_vicuna_70k_unfiltered, ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split, openai/summarize_from_feedback, ehartford/dolphin
Input Output
Input Format: " ***System:" for system messages, " ***Query:" for user queries, " ***Response:" for assistant responses.
Performance Tips: It's important to maintain the correct whitespace as "***" and " ***" represent different tokens.
LLM Name Ypotryll 22B Gptq Repository 🤗 https://huggingface.co/chargoddard/ypotryll-22b-gptq Merged Model Yes Model Size 22b Required VRAM 12 GB Updated 2026-08-01 Maintainer chargoddard Model Type llama Instruction-Based Yes Model Files 12.0 GB GPTQ Quantization Yes Quantization Type gptq|4bit Model Architecture LlamaForCausalLM Context Length 4098 Model Max Length 4098 Transformers Version 4.32.0.dev0 Tokenizer Class LlamaTokenizer Beginning of Sentence Token <s> End of Sentence Token </s> Unk Token <unk> Vocabulary Size 32000 Torch Data Type float16
Rank the Ypotryll 22B Gptq capabilities
Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.
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
Best Alternatives to Ypotryll 22B Gptq
Note: green Score (e.g. "73.2 ") means that the model is better than chargoddard/ypotryll-22b-gptq .
Expand