LLM Name | Model |
Repository | Open on ๐ค |
Model Size | 6b |
Required VRAM | 6.2 GB |
Updated | 2024-07-27 |
Maintainer | kanayatmd |
Model Type | gptj |
Model Files | |
Quantization Type | 8bit |
Model Architecture | GPTJForCausalLM |
Transformers Version | 4.18.0 |
Tokenizer Class | GPT2Tokenizer |
Vocabulary Size | 50400 |
Torch Data Type | float32 |
Activation Function | gelu_new |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...oduct NER GPT J 6B 4bit Merged | 0.2 | 0K / 2.5 GB | 21 | 0 |
...nese Novel GPT J 6B F16 Marisa | 0.2 | 0K / 12.2 GB | 30 | 4 |
Kakaobrain Kogpt 6B 8bit | 0.1 | 0K / 6.7 GB | 67 | 1 |
Pygmalion 6b Dev 4bit 128g | 0.1 | 0K / 4 GB | 175 | 121 |
GPT J 6B Skein 4bit 128g | 0.1 | 0K / 4 GB | 29 | 1 |
Pygmalion 6B 4bit 128g | 0.1 | 0K / 4 GB | 63 | 39 |
GPT J 6B Alpaca Gpt4 | 0.1 | 0K / 24.3 GB | 10 | 19 |
Pygmalion 6B 4bit 128g | 0.1 | 0K / 4 GB | 21 | 3 |
Dolly Shygmalion 6B 4bit 128g | 0.1 | 0K / 4 GB | 9 | 5 |
PPO Pygway 6B Mix 4bit 128g | 0.1 | 0K / 4 GB | 12 | 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