ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
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
7 derivatives checked
- ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1-GGUF: Same weights, converted
- QuantFactory/Turkish-Llama-8b-Instruct-v0.1-GGUF: Quantization
- mradermacher/Turkish-Llama-8b-Instruct-v0.1-GGUF: Full fine-tune
- ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1: Full fine-tune
- matrixportalx/Turkish-Llama-8b-Instruct-v0.1-GGUF: Same weights, converted
- featherless-ai-quants/ytu-ce-cosmos-Turkish-Llama-8b-Instruct-v0.1-GGUF: Quantization
- tensorblock/Turkish-Llama-8b-Instruct-v0.1-GGUF: Quantization
3 other repos hold byte-for-byte identical weight files.