Nexusflow/Athene-70B
Full fine-tune vs meta-llama/Meta-Llama-3-70B-Instruct. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 96/161, MLP 240/240, Attention 320/320, lm_head 1/1
10 derivatives checked
- mradermacher/Athene-70B-i1-GGUF: Full fine-tune
- legraphista/Athene-70B-IMat-GGUF: Same weights, converted
- bartowski/Athene-70B-GGUF: Quantization
- mradermacher/Athene-70B-GGUF: Full fine-tune
- featherless-ai-quants/Nexusflow-Athene-70B-GGUF: Quantization
- lmstudio-community/Athene-70B-GGUF: Full fine-tune
- gbueno86/Cathallama-70B: Full fine-tune
- Nexesenex/Llama_3.x_70b_L3.3_Athene_128K_v1.02: Full fine-tune
- Nexesenex/Llama_3.x_70b_Tess_Athene_128K_v1.0: Full fine-tune
- Nexesenex/Llama_3.x_70b_Tess_Athene_128K_v1.02: Full fine-tune