Pyg Instruct Wizardlm is an open-source language model by Lazycuber. Features: 6b LLM, VRAM: 12.2GB, Instruction-Based, LLM Explorer Score: 0.11, Arc: 41, HellaSwag: 66.7, MMLU: 26.3, GSM8K: 1.6.
| LLM Name | Pyg Instruct Wizardlm |
| Repository 🤗 | https://huggingface.co/Lazycuber/pyg-instruct-wizardlm |
| Model Size | 6b |
| Required VRAM | 12.2 GB |
| Updated | 2026-07-28 |
| Maintainer | Lazycuber |
| Model Type | gptj |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | GPTJForCausalLM |
| Model Max Length | 1024 |
| Transformers Version | 4.28.1 |
| Tokenizer Class | GPT2Tokenizer |
| Beginning of Sentence Token | <|endoftext|> |
| End of Sentence Token | <|endoftext|> |
| Unk Token | <|endoftext|> |
| Vocabulary Size | 50402 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu_new |
| Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| GPT J 6B Alpaca Gpt4 | 0K / 24.3 GB | 46 | 20 |
| Zenos GPT J 6B Instruct 4bit | 0K / 3.4 GB | 2 | 1 |