Noticing the annoying behaviors found in Nightwing3 with this as well. Might retrain from virtuoso direct.

image/png

Prompt format: ChatML

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Quants: None

ST Presets [Updated] Here

image/png

Base model: Nitral-AI/NightWing3-R1_Virtuoso-10B-v0.3-e1

Lora was merged using the passthrough method; The following YAML configuration was used to produce this model:

Nitral-AI/NightWing3-R1_Virtuoso-10B-v0.3-e1 + Nitrals-Loras/NightWing3-R1_Virtuoso-10B-v0.3e2-lora as a base.

base_model: Nitral-AI/NightWing3-R1_Virtuoso-10B-v0.3-e1+Nitrals-Loras/NightWing3-R1_Virtuoso-10B-v0.3e2-lora
dtype: bfloat16
merge_method: passthrough
models:
  - model: Nitral-AI/NightWing3-R1_Virtuoso-10B-v0.3-e1+Nitrals-Loras/NightWing3-R1_Virtuoso-10B-v0.3e2-lora
Downloads last month
47
Safetensors
Model size
10.3B params
Tensor type
BF16
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Nitral-Archive/NightWing3-R1_Virtuoso-10B-v0.3e2

Spaces using Nitral-Archive/NightWing3-R1_Virtuoso-10B-v0.3e2 3