Groq/Llama-3-Groq-8B-Tool-Use
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
9 derivatives checked
- lmstudio-community/Llama-3-Groq-8B-Tool-Use-GGUF: Quantization
- bartowski/Llama-3-Groq-8B-Tool-Use-GGUF: Quantization
- mradermacher/Llama-3-Groq-8B-Tool-Use-GGUF: Same weights, converted
- MaziyarPanahi/Llama-3-Groq-8B-Tool-Use-GGUF: Same weights, converted
- mradermacher/Llama-3-Groq-8B-Tool-Use-i1-GGUF: Quantization
- lmstudio-community/Llama-3-Groq-70B-Tool-Use-GGUF: Not comparable yet
- second-state/Llama-3-Groq-8B-Tool-Use-GGUF: Same weights, converted
- gaianet/Llama-3-Groq-8B-Tool-Use-GGUF: Same weights, converted
- tensorblock/Llama-3-Groq-8B-Tool-Use-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.