Instructions to use QuantFactory/magnum-v4-12b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/magnum-v4-12b-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="QuantFactory/magnum-v4-12b-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/magnum-v4-12b-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/magnum-v4-12b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/magnum-v4-12b-GGUF",
	filename="magnum-v4-12b.Q2_K.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/magnum-v4-12b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/magnum-v4-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/magnum-v4-12b-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 QuantFactory/magnum-v4-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/magnum-v4-12b-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 QuantFactory/magnum-v4-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/magnum-v4-12b-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 QuantFactory/magnum-v4-12b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/magnum-v4-12b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/magnum-v4-12b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/magnum-v4-12b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/magnum-v4-12b-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": "QuantFactory/magnum-v4-12b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/magnum-v4-12b-GGUF:Q4_K_M

SGLang

How to use QuantFactory/magnum-v4-12b-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "QuantFactory/magnum-v4-12b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/magnum-v4-12b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "QuantFactory/magnum-v4-12b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/magnum-v4-12b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/magnum-v4-12b-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/magnum-v4-12b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/magnum-v4-12b-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 QuantFactory/magnum-v4-12b-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 QuantFactory/magnum-v4-12b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/magnum-v4-12b-GGUF to start chatting

Pi new

How to use QuantFactory/magnum-v4-12b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf QuantFactory/magnum-v4-12b-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": "QuantFactory/magnum-v4-12b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use QuantFactory/magnum-v4-12b-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 QuantFactory/magnum-v4-12b-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 QuantFactory/magnum-v4-12b-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use QuantFactory/magnum-v4-12b-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/magnum-v4-12b-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/magnum-v4-12b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/magnum-v4-12b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.magnum-v4-12b-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/magnum-v4-12b-GGUF

This is quantized version of anthracite-org/magnum-v4-12b created using llama.cpp

Original Model Card

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus.

This model is fine-tuned on top of mistralai/Mistral-Nemo-Instruct-2407.

Prompting

A typical input would look like this:

<s>[INST] SYSTEM MESSAGE
USER MESSAGE[/INST] ASSISTANT MESSAGE</s>[INST] USER MESSAGE[/INST]

SillyTavern templates

Below are Instruct and Context templates for use within SillyTavern.

context template

default SillyTavern template works fine

instruct template

default SillyTavern template works fine

Axolotl config

See axolotl config

base_model: mistralai/Mistral-Nemo-Instruct-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: anthracite-org/magnum-v4-12b-r2
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system
    type: custommistralv3tekken
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
    type: custommistralv3tekken
  - path: anthracite-org/kalo-opus-instruct-3k-filtered-no-system
    type: custommistralv3tekken
  - path: anthracite-org/nopm_claude_writing_fixed
    type: custommistralv3tekken
  - path: anthracite-org/kalo_opus_misc_240827_no_system
    type: custommistralv3tekken
  - path: anthracite-org/kalo_misc_part2_no_system
    type: custommistralv3tekken
#chat_template: chatml
shuffle_merged_datasets: true
#default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: /workspace/data/magnum-12b-data
val_set_size: 0.0
output_dir: /workspace/data/12b-fft-out

sequence_len: 32768
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project: 12b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: v4-r2-attempt-01
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: deepspeed_configs/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  pad_token: <pad>

Credits

We'd like to thank Recursal / Featherless for sponsoring the compute for this train, Featherless has been hosting our Magnum models since the first 72 B and has given thousands of people access to our models and helped us grow.

We would also like to thank all members of Anthracite who made this finetune possible.

Datasets

Training

The training was done for 2 epochs. We used 8xH100s GPUs graciously provided by Recursal AI / Featherless AI for the full-parameter fine-tuning of the model.

Safety

...

Downloads last month: 107

GGUF

Model size

12B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit