LLM Name | Fikri 3.1 8B Instruct |
Repository ๐ค | https://huggingface.co/BrewInteractive/fikri-3.1-8B-Instruct |
Base Model(s) | |
Merged Model | Yes |
Model Size | 8b |
Required VRAM | 16.1 GB |
Updated | 2024-10-11 |
Maintainer | BrewInteractive |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | tr |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | llama3.1 |
Context Length | 8192 |
Model Max Length | 8192 |
Transformers Version | 4.43.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|reserved_special_token_250|> |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...B Instruct Gradient 1048K 4bit | 1024K / 4.5 GB | 1 | 2 |
...B Instruct Gradient 1048K 8bit | 1024K / 8.6 GB | 5 | 1 |
...truct Gradient 1048K Bpw6 EXL2 | 1024K / 6.7 GB | 5 | 2 |
...truct Gradient 1048K Bpw5 EXL2 | 1024K / 5.8 GB | 5 | 0 |
Llama 3 8B Instruct 1048K 4bit | 1024K / 4.5 GB | 7 | 25 |
Llama 3 8B Instruct 1048K 8bit | 1024K / 8.6 GB | 8 | 16 |
... Gradient 1048K 8.0bpw H8 EXL2 | 1024K / 8.6 GB | 2 | 3 |
...ct Gradient 1048K Bpw2.25 EXL2 | 1024K / 3.4 GB | 9 | 1 |
...Instruct 262K HQQ 2bit Smashed | 256K / 4 GB | 27 | 2 |
Llama 3 8B Instruct 262K 2bit | 256K / 2.5 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