Nexesenex/Llama_3.3_70b_DeepSeek_R1_Dropable_V1.01
LoRA-style vs TheDrummer/Fallen-Llama-3.3-R1-70B-v1. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 80 of 80 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320, lm_head 0/1
4 derivatives checked
- mradermacher/Llama_3.3_70b_DeepSeek_R1_Dropable_V1.01-i1-GGUF: Quantization
- mradermacher/Llama_3.3_70b_DeepSeek_R1_Dropable_V1.01-GGUF: Quantization
- NexesMess/Llama_3.x_70b_SmarTracks_0.21: Full fine-tune
- Nexesenex/Llama_3.x_70b_SmarTracks_v1.30_flat: Full fine-tune