LLM Name | EEVE Korean Instruct 10.8B V1.0 |
Repository ๐ค | https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0 |
Base Model(s) | |
Model Size | 10.8b |
Required VRAM | 21.6 GB |
Updated | 2024-09-07 |
Maintainer | yanolja |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.36.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 40960 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...Korean Instruct 10.8B V1.0 AWQ | 0 | 46 | 6 GB |
...truct 10.8B Geoheim7 8bit Gguf | 0 | 0 | 11 GB |
...n Instruct 10.8B Geoheim7 8bit | 0 | 0 | 21 GB |
...truct 10.8B Geoheim6 8bit Gguf | 0 | 0 | 11 GB |
...truct 10.8B Geoheim5 8bit Gguf | 0 | 0 | 11 GB |
...truct 10.8B Geoheim4 8bit Gguf | 0 | 0 | 11 GB |
...ruct 10.8B Geoheim20 8bit Gguf | 0 | 0 | 11 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...Korean Instruct 10.8B V1.0 32K | 32K / 21.6 GB | 27 | 10 |
AlgograpV4 | 4K / 43.2 GB | 2008 | 0 |
Eeve Leaderboard Inst V1.5 | 4K / 21.6 GB | 1977 | 0 |
Eeve DPO V3 | 4K / 21.6 GB | 1977 | 0 |
Hkcode Meta QA5 | 4K / 21.6 GB | 10 | 0 |
...struct 10.8B V1.0 Empathy V0.1 | 4K / 21.6 GB | 6 | 0 |
EEVE Korean Instruct 10.8B Var | 4K / 21.6 GB | 25 | 3 |
EEVE 10.8 BOOK V0.1 | 4K / 21.6 GB | 5 | 1 |
EEVE Instruct Math 10.8B | 4K / 21.6 GB | 5 | 3 |
...n Instruct 10.8B Geoheim7 8bit | 4K / 21.6 GB | 0 | 0 |
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