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
22
Safetensors
Model size
10.3B params
Tensor type
BF16
ยท
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

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

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