Instructions to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF",
	filename="Musica-27b-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Ollama
How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with Ollama:
```
ollama run hf.co/LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M
```

Unsloth Studio new

How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF to start chatting

Pi new

How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M
```

Lemonade

How to use LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF-Q4_K_M

List all available models

lemonade list

GGUF Quants of Qwen 3.5 27B Musica v1

Using llama.cpp release b8533, non iMatrix quants.

Original Model: https://huggingface.co/AuriAetherwiing/TQ3.5-27B-Musica-v1

Personal favorite of mine too, I really like this model! Thanks Auri!

Original Model Card Below

Qwen3.5-27B Musica v1

RP/storygen/conversational tune of Qwen3.5-27B. Stylewise looked pretty nice to me and seems decently steerable, should also reduce refusal rate even further than derestricted ver on which it was based on. Both reasoning and non-reasoning modes are supported, reasoning mode even has several styes of reasoning, reroll to see them (perhaps I should mark them to make them manually evokable on next iter?). Might or might not have slightly better world knowledge than base, lol.

This training run was sponsored by ArliAI

Wishlist for next iter - more conversational reasoning data (and more reasoning data in general) and perhaps something multiturn for creative writing. Perhaps also train Qwen3.5-9B and Nemotron-3-Super-120B-A12B before iterating on dataset.

Training notes

Rank 64, alpha 64 LoRA on top of ArliAI's Derestricted version, for two epochs with constant scheduler. Training took ~17 hours on OwenArli's 2xRTX Pro 6000 Blackwell.

Run's graphs on Comet (DW about that API key in config, I deactivated it before sharing this lol)

Recommended samplers

Temperature: 1
NSigma: 2
Min-P: 0.02

Axolotl config

See Axolotl config

base_model: /home/arli/models/Qwen3.5-27B-Derestricted

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
cut_cross_entropy: true
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true

load_in_8bit: false
load_in_4bit: false

shuffle_merged_datasets: true
datasets:
  - path: ./musica-nonreasoning-sft-megafix.jsonl
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value
  - path: ./musica-reasoning-sft-fix.jsonl
    type: chat_template
    field_messages: conversations
    message_property_mappings:
      role: from
      content: value

dataset_prepared_path: ./last_run_prepared
val_set_size: 0
output_dir: ./outputs/v1
adapter: lora
save_safetensors: true

sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true

lora_r: 64
lora_alpha: 64
lora_dropout: 0.0
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - down_proj
  - up_proj
  # Uncomment below to also target the linear attention projections.
  # These use separate in_proj_qkv / in_proj_z / out_proj (Qwen3.5-specific).
  # - linear_attn.in_proj_qkv
  # - linear_attn.in_proj_z
  # - linear_attn.out_proj

lora_mlp_kernel: false
lora_qkv_kernel: false
lora_o_kernel: false

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_torch_fused
lr_scheduler: constant
learning_rate: 4e-6
max_grad_norm: 0.5

bf16: auto

use_comet: true
comet_project_name: musica-27b

auto_resume_from_checkpoints: false
logging_steps: 1
flash_attention: true

warmup_ratio: 0
evals_per_epoch: 0
saves_per_epoch: 4
save_total_limit: 4

gradient_checkpointing: false
gradient_checkpointing_kwargs:
  use_reentrant: false

fsdp_config:
  fsdp_version: 2
  offload_params: false
  cpu_ram_efficient_loading: false
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: Qwen3_5DecoderLayer
  state_dict_type: FULL_STATE_DICT
  sharding_strategy: FULL_SHARD
  reshard_after_forward: true
  activation_checkpointing: true

Downloads last month: 213

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF

Base model

Qwen/Qwen3.5-27B

Finetuned

ArliAI/Qwen3.5-27B-Derestricted

Finetuned

AuriAetherwiing/TQ3.5-27B-Musica-v1

Quantized

(6)

this model

LyraNovaHeart
/

AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF

Model tree for LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF

Datasets used to train LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF