LLM Name | Llama 3 Open Ko 8B |
Repository ๐ค | https://huggingface.co/beomi/Llama-3-Open-Ko-8B |
Model Size | 8b |
Required VRAM | 16 GB |
Updated | 2024-10-18 |
Maintainer | beomi |
Model Type | llama |
Model Files | |
Supported Languages | en ko |
Model Architecture | LlamaForCausalLM |
License | other |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.40.1 |
Tokenizer Class | PreTrainedTokenizerFast |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Llama 3 Open Ko 8B Gguf | 33 | 3728 | 4 GB |
...n Ko 8B Instruct VBiom V1 Gguf | 0 | 42 | 16 GB |
...8B Instruct AlphaEdu100V3 Gguf | 0 | 36 | 16 GB |
...en Ko 8B Instruct Kookmin Gguf | 0 | 34 | 8 GB |
...3 Ko Bemoi 8B VBioLLM1000 Gguf | 0 | 18 | 16 GB |
...n Ko 8B Instruct Kookmin2 Gguf | 0 | 26 | 8 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...a 3 8B Instruct Gradient 1048K | 1024K / 16.1 GB | 7568 | 667 |
L3.1 Gradient | 1024K / 16.1 GB | 5 | 0 |
Llama3 8B Special Dark V3.1.2a | 1024K / 16.1 GB | 130 | 0 |
Llama3 8B Special Dark RP2 | 1024K / 16.1 GB | 99 | 1 |
Llama3 8B Special Dark V3.1.1t | 1024K / 16.1 GB | 100 | 0 |
Loki V2.1 | 1024K / 16.1 GB | 8 | 0 |
Llama3 8B Special Dark RP1 | 1024K / 16.1 GB | 57 | 0 |
...SLERP Gradient1048k OpenBioLLM | 1024K / 16.1 GB | 21 | 0 |
Llama3 8B Special Dark V2.0 | 1024K / 16.1 GB | 95 | 0 |
Llama3 8B Special Dark V3.1.2c | 1024K / 16.1 GB | 3 | 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