LLM Name | Kakaobrain Kogpt 6B 8bit |
Repository ๐ค | https://huggingface.co/rycont/kakaobrain__kogpt-6b-8bit |
Model Size | 6b |
Required VRAM | 6.7 GB |
Updated | 2024-09-07 |
Maintainer | rycont |
Model Type | gptj |
Model Files | |
Quantization Type | 8bit |
Model Architecture | GPTJForCausalLM |
Transformers Version | 4.29.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | [PAD] |
Vocabulary Size | 64512 |
Torch Data Type | float16 |
Activation Function | gelu_new |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Model | 0K / 6.2 GB | 6 | 0 |
...oduct NER GPT J 6B 4bit Merged | 0K / 2.5 GB | 6 | 0 |
...nese Novel GPT J 6B F16 Marisa | 0K / 12.2 GB | 11 | 4 |
Pygmalion 6b Dev 4bit 128g | 0K / 4 GB | 127 | 121 |
GPT J 6B Skein 4bit 128g | 0K / 4 GB | 14 | 1 |
GPT J 6B Alpaca Gpt4 | 0K / 24.3 GB | 31 | 20 |
Pygmalion 6B 4bit 128g | 0K / 4 GB | 9 | 3 |
Pygmalion 6B 4bit 128g | 0K / 4 GB | 42 | 39 |
Dolly Shygmalion 6B 4bit 128g | 0K / 4 GB | 6 | 5 |
PPO Pygway 6B Mix 4bit 128g | 0K / 4 GB | 11 | 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