| Additional Notes |
|
| LLM Name | GenAI Llama2 Ko En Instruct 20B V1 |
| Repository ๐ค | https://huggingface.co/42MARU/GenAI-llama2-ko-en-instruct-20B-v1 |
| Model Size | 20b |
| Required VRAM | 40.4 GB |
| Updated | 2025-09-22 |
| Maintainer | 42MARU |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.34.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 46336 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Bagel 20B V04 Llama | 32K / 39.6 GB | 12 | 7 |
| Bagel DPO 20B V04 Llama | 32K / 39.6 GB | 7 | 3 |
| ...lm2 1.7B Distilled GPT Oss 20B | 8K / 0 GB | 25 | 2 |
| ...runed Base PostPruneRetraining | 8K / 0 GB | 5 | 0 |
| ...lerLM 20M Instruct Pruned Sft5 | 8K / 0.1 GB | 6 | 0 |
| Rose 20B | 4K / 39.9 GB | 1869 | 42 |
| Rose 20B GPTQ | 4K / 10.5 GB | 597 | 3 |
| Rose 20B AWQ | 4K / 10.9 GB | 7 | 1 |
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