Downloads · 30 days
0
Horiznsky/Serenity-Llama-3.2-3B-Counsel
Serenity-Llama-3.2-3B-Counsel is a machine learning model from Horiznsky. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Model Name: Serenity-Llama-3.2-3B-Counsel Base Model: unsloth/Llama-3.2-3B-Instruct Model Type: Fine-tuned Causal Language Model Format: GGUF (Quantized Q4KM) License: MIT
Downloads · 30 days
0
Access
Public
Updated Jun 20, 2026
Repo size
—
Likes
0
Public
Click a slice to open those files.
.md2 KB · 57%
From the Hugging Face model README
This model is a specialized, privacy-focused mental health assistant. It was fine-tuned to provide empathetic, evidence-based responses to mental health-related inquiries, grounded in clinical guidelines[cite: 1]. The model is optimized for local deployment on consumer hardware[cite: 1].
r = 16, lora_alpha = 16, lora_dropout = 0, bias = "none"[cite: 1]max_steps = 60, learning_rate = 2e-4, batch_size = 2 (with 4x gradient accumulation)[cite: 1]This model is designed to be used with llama.cpp or compatible UI frameworks like LM Studio.
<|start_header_id|>user<|end_header_id|>
{user_query}<|eot_id|><|start_header_id|>assistant<|end_header_id|>