LLM Name | FTAudit Vuln Llama3 8B V0.3 |
Repository ๐ค | https://huggingface.co/weifar/FTAudit-Vuln-Llama3-8b-v0.3 |
Model Size | 8b |
Required VRAM | 4.1 GB |
Updated | 2024-09-06 |
Maintainer | weifar |
Model Type | mistral |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 4bit |
Model Architecture | MistralForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.41.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | [control_768] |
Vocabulary Size | 32768 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Model | 32K / 30.6 GB | 5 | 0 |
Phi3 Mini 4bit COIG CQIA | 4K / 2.3 GB | 5 | 0 |
Hathor V3.4 | 32K / 14.5 GB | 6 | 0 |
Hathor V4 | 32K / 14.5 GB | 6 | 0 |
Test | 32K / 7.6 GB | 764 | 0 |
Tor 8B | 16K / 16.8 GB | 61 | 1 |
...tral NeMo Minitron 8B Instruct | 8K / 16.8 GB | 1921 | 45 |
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