LLM Name | Unhinged Llama3 8B 524K |
Repository ๐ค | https://huggingface.co/FiditeNemini/Unhinged-Llama3-8B-524K |
Base Model(s) | |
Merged Model | Yes |
Model Size | 8b |
Required VRAM | 26.5 GB |
Updated | 2024-07-24 |
Maintainer | FiditeNemini |
Model Type | llama |
Model Files | |
GGUF Quantization | Yes |
Quantization Type | q8|gguf |
Model Architecture | LlamaForCausalLM |
Context Length | 524288 |
Model Max Length | 524288 |
Transformers Version | 4.40.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|end_of_text|> |
Vocabulary Size | 128258 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...truct Gradient 1048K IMat GGUF | 1024K / 2 GB | 245 | 6 |
...B Instruct Gradient 1048K GGUF | 1024K / 3.2 GB | 224 | 3 |
Llama 3 8B Instruct 262K GGUF | 256K / 3.2 GB | 4813 | 2 |
Alpaca Llama3.1 8B | 128K / 16.1 GB | 306 | 0 |
L3.1 RP Test | 128K / 16.1 GB | 22 | 0 |
Alpha R S V2 Q8 0 GGUF | 39K / 8.5 GB | 12 | 0 |
Llama 3 Cantonese 8B Instruct | 8K / 16.1 GB | 64 | 1 |
Llama 3 Open Ko 8B Gguf | 8K / 4.7 GB | 3381 | 30 |
...ama3 8B Chinese Chat GGUF 8bit | 8K / 8.5 GB | 825 | 160 |
DiarizationLM 8B Fisher V1 | 8K / 16.1 GB | 173 | 2 |
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