openchat/openchat-3.6-8b-20240522
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
9 derivatives checked
- legraphista/openchat-3.6-8b-20240522-IMat-GGUF: Same weights, converted
- QuantFactory/openchat-3.6-8b-20240522-GGUF: Quantization
- featherless-ai-quants/openchat-openchat-3.6-8b-20240522-GGUF: Quantization
- mradermacher/openchat-3.6-8b-20240522-i1-GGUF: Quantization
- mradermacher/openchat-3.6-8b-20240522-GGUF: Same weights, converted
- qwp4w3hyb/openchat-3.6-8b-20240522-iMat-GGUF: Same weights, converted
- NeuralNet-Hub/openchat-3.6-8b-20240522-GGUF: Same weights, converted
- lmstudio-community/openchat-3.6-8b-20240522-GGUF: Quantization
- MaziyarPanahi/openchat-3.6-8b-20240522-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.