LLM Name | EEVE Korean 10.8B RAFT |
Repository ๐ค | https://huggingface.co/ai-human-lab/EEVE-Korean-10.8B-RAFT |
Model Size | 10.8b |
Required VRAM | 43.2 GB |
Updated | 2024-12-08 |
Maintainer | ai-human-lab |
Model Type | llama |
Model Files | |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.41.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 40962 |
Torch Data Type | float32 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...Korean Instruct 10.8B V1.0 32K | 32K / 21.6 GB | 82 | 10 |
EEVE Korean 10.8B V1.0 16K | 16K / 21.6 GB | 21 | 0 |
...EVE Korean Instruct 10.8B V1.0 | 4K / 21.6 GB | 26192 | 137 |
...Judgment Transducer 10.8B V2.0 | 4K / 21.6 GB | 120 | 0 |
T3Q LLM1 CV V1.0 | 4K / 21.6 GB | 9657 | 0 |
T3Q LLM1 CV V2.0 | 4K / 21.6 GB | 5017 | 0 |
EEVE Ver 4.1 Sft | 4K / 21.6 GB | 5016 | 0 |
T3Q LLM Sft1.0 Dpo1.0 | 4K / 21.6 GB | 5030 | 0 |
T3Q LLM Solar10.8 Sft V1.0 | 4K / 21.6 GB | 5016 | 0 |
AlgograpV4 | 4K / 43.2 GB | 5023 | 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