LLM Name | Llama 2 Ko Instruct 13B |
Repository | Open on ๐ค |
Model Size | 13b |
Required VRAM | 26.2 GB |
Updated | 2024-07-27 |
Maintainer | daekeun-ml |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | ko |
Model Architecture | LlamaForCausalLM |
License | llama2 |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.34.1 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 46336 |
Torch Data Type | float16 |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
NexusRaven V2 13B | 0.3 | 16K / 26 GB | 6412 | 454 |
CodeLlama 13B Instruct Hf | 0.3 | 16K / 26 GB | 25146 | 142 |
CodeLlama 13B Instruct Hf | 0.3 | 16K / 26 GB | 2027 | 10 |
TableLLM 13B | 0.2 | 16K / 26 GB | 90 | 18 |
NexusRaven 13B | 0.2 | 16K / 26 GB | 193 | 100 |
... Llama 2 13B Instruct Text2sql | 0.2 | 16K / 26 GB | 342 | 26 |
Panda Coder 13B | 0.2 | 16K / 26 GB | 13 | 13 |
Gen Sim | 0.2 | 16K / 0.3 GB | 44 | 2 |
Llama 3 13B Instruct Ft | 0.3 | 8K / 26.1 GB | 244 | 2 |
Llama 3 13B Instruct | 0.2 | 8K / 26.5 GB | 237 | 3 |
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