Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1

Partial fine-tune vs KingNish/Reasoning-Llama-1b-v0.1. Partial change: 79% of the weights changed (attention, mlp, norms), in 16 of 16 layers.

Tensors changed: Embeddings 0/1, Norms 9/33, MLP 48/48, Attention 64/64

3 derivatives checked

• mradermacher/Llama_3.2_1b_OpenTree_R1_0.1-i1-GGUF: Quantization
• Nexesenex/Llama_3.2_1b_OpenTree_R1_0.1-GGUF: Full fine-tune
• mradermacher/Llama_3.2_1b_OpenTree_R1_0.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse