license: apache-2.0 base_model: richardyoung/granite-4.2-3b-heretic datasets:

Minas2025 Granite 4.2 3B WarmChat (Q6_K GGUF)

Conversational fine-tune of Granite 4.2 3B for warm, natural chat. Trained with Unsloth QLoRA on an AMD RX 6700 XT.

Files

File	Size	What
`Minas2025-Granite-4.2-3B-WarmChat-Q6_K.gguf`	~3.0 GB	Main model, Q6_K quant. Load this.

richardyoung/granite-4.2-3b-heretic

Method: QLoRA, rank 16, alpha 16, dropout 0.0; all attention+MLP projections (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)
Optimizer: AdamW 8-bit, LR 1.5e-4, cosine schedule, 10 warmup steps
1150 steps, batch size 1, gradient accumulation 8, max seq length 2048
Data: ~11,400 conversational rows (train) / 600 rows (eval)
Eval loss falling through the full run, no overfit
Export: adapters merged to F16, quantized to Q6_K with llama.cpp

Load the Q6_K file directly. Chat template included. Context up to 2048 tokens (trained length).

File

Size

What

Minas2025-Granite-4.2-3B-WarmChat-Q6_K.gguf

~3.0 GB

Main model, Q6_K quant. Load this.

Training recipe

Method: QLoRA, rank 16, alpha 16, dropout 0.0; all attention+MLP projections (q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)

Optimizer: AdamW 8-bit, LR 1.5e-4, cosine schedule, 10 warmup steps

1150 steps, batch size 1, gradient accumulation 8, max seq length 2048

Data: ~11,400 conversational rows (train) / 600 rows (eval)

Eval loss falling through the full run, no overfit

Export: adapters merged to F16, quantized to Q6_K with llama.cpp