Model Card on HF 🤗: https://huggingface.co/rycont/kakaobrain__kogpt-6b-8bit
Kakaobrain Kogpt 6B 8bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Kakaobrain Kogpt 6B 8bit Parameters and Internals
| LLM Name | Kakaobrain Kogpt 6B 8bit |
| Repository 🤗 | https://huggingface.co/rycont/kakaobrain__kogpt-6b-8bit |
| Model Size | 6b |
| Required VRAM | 6.7 GB |
| Updated | 2025-06-09 |
| 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 to Kakaobrain Kogpt 6B 8bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Model | 0K / 6.2 GB | 16 | 0 |
| ...oduct NER GPT J 6B 4bit Merged | 0K / 2.5 GB | 28 | 0 |
| ...nese Novel GPT J 6B F16 Marisa | 0K / 12.2 GB | 16 | 3 |
| Pygmalion 6b Dev 4bit 128g | 0K / 4 GB | 29 | 120 |
| GPT J 6B Skein 4bit 128g | 0K / 4 GB | 11 | 1 |
| GPT J 6B Alpaca Gpt4 | 0K / 24.3 GB | 22 | 20 |
| Pygmalion 6B 4bit 128g | 0K / 4 GB | 26 | 3 |
| Pygmalion 6B 4bit 128g | 0K / 4 GB | 49 | 40 |
| Dolly Shygmalion 6B 4bit 128g | 0K / 4 GB | 11 | 5 |
| PPO Pygway 6B Mix 4bit 128g | 0K / 4 GB | 21 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than rycont/kakaobrain__kogpt-6b-8bit .
Rank the Kakaobrain Kogpt 6B 8bit Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 48046 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124