8bit Base model:yanolja/eeve-korean... En Endpoints compatible Gguf Instruct License:apache-2.0 Llama Q8 Quantized Region:us Unsloth
Model Card on HF 🤗: https://huggingface.co/jay6944/EEVE-Korean-Instruct-10.8B-geoheim20-8bit-gguf
EEVE Korean Instruct 10.8B Geoheim20 8bit Gguf Parameters and Internals
| LLM Name | EEVE Korean Instruct 10.8B Geoheim20 8bit Gguf |
| Repository 🤗 | https://huggingface.co/jay6944/EEVE-Korean-Instruct-10.8B-geoheim20-8bit-gguf |
| Base Model(s) | |
| Model Size | 10.8b |
| Required VRAM | 11.5 GB |
| Updated | 2024-07-04 |
| Maintainer | jay6944 |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | gguf|q8|8bit |
| Model Architecture | AutoModel |
| License | apache-2.0 |
Best Alternatives to EEVE Korean Instruct 10.8B Geoheim20 8bit Gguf
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mergekit Slerp Ieauevl GGUF | 0K / 2.7 GB | 38 | 0 |
| ...truct 10.8B Geoheim5 8bit Gguf | 0K / 11.5 GB | 0 | 0 |
| ...truct 10.8B Geoheim7 8bit Gguf | 0K / 11.5 GB | 0 | 0 |
| ...truct 10.8B Geoheim4 8bit Gguf | 0K / 11.5 GB | 0 | 0 |
| ...truct 10.8B Geoheim6 8bit Gguf | 0K / 11.5 GB | 0 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than jay6944/EEVE-Korean-Instruct-10.8B-geoheim20-8bit-gguf .
Rank the EEVE Korean Instruct 10.8B Geoheim20 8bit Gguf 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124