Views
No views yet
safetensors) weights for Rudy-Nemo-12B-v1, intended for further merging, fine-tuning, or high-precision inference.Looking for ready-to-run GGUF files? > Check out the GGUF repository for LM Studio, Ollama, and llama.cpp:
RoseRudolph/rudy-nemo-12b-v1
1slices:
2 - sources:
3 - model: mistralai/Mistral-Nemo-Instruct-2407
4 layer_range: [0, 40]
5 - model: TheDrummer/Rocinante-12B-v1.1
6 layer_range: [0, 40]
7
8merge_method: slerp
9base_model: mistralai/Mistral-Nemo-Instruct-2407
10tokenizer_source: base
11
12parameters:
13 t:
14 - filter: self_attn
15 value: [0.00, 0.25, 0.50, 0.75, 1.00]
16 - filter: mlp
17 value: [0.00, 0.25, 0.50, 0.75, 1.00]
18 - value: 0.50
19
20dtype: bfloat16