Instructions to use mrcuddle/lummaid-fusion-14B-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mrcuddle/lummaid-fusion-14B-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("mrcuddle/arcee-fusion-lumaid-12B")
model = PeftModel.from_pretrained(base_model, "mrcuddle/lummaid-fusion-14B-lora")

Transformers

How to use mrcuddle/lummaid-fusion-14B-lora with Transformers:

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

pipe = pipeline("text-generation", model="mrcuddle/lummaid-fusion-14B-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mrcuddle/lummaid-fusion-14B-lora")
model = AutoModelForCausalLM.from_pretrained("mrcuddle/lummaid-fusion-14B-lora", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mrcuddle/lummaid-fusion-14B-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrcuddle/lummaid-fusion-14B-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mrcuddle/lummaid-fusion-14B-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mrcuddle/lummaid-fusion-14B-lora

SGLang

How to use mrcuddle/lummaid-fusion-14B-lora 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 "mrcuddle/lummaid-fusion-14B-lora" \
    --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": "mrcuddle/lummaid-fusion-14B-lora",
		"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 "mrcuddle/lummaid-fusion-14B-lora" \
        --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": "mrcuddle/lummaid-fusion-14B-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mrcuddle/lummaid-fusion-14B-lora with Docker Model Runner:
```
docker model run hf.co/mrcuddle/lummaid-fusion-14B-lora
```

See axolotl config

axolotl version: 0.18.0

adapter: qlora
base_model: mrcuddle/arcee-fusion-lumaid-12B
bf16: false
chat_template: mistral_v2v3
dataloader_num_workers: 2
dataloader_pin_memory: true
dataloader_prefetch_factor: 8
datasets:
- eot_tokens:
  - <|im_end|>
  field: story
  path: bluuwhale/nsfwstory2
  split: train
  type: completion
embeddings_skip_upcast: true
fp16: true
gradient_accumulation_steps: 1
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
learning_rate: 0.00019
load_in_4bit: true
logging_steps: 1
lora_alpha: 64
lora_mlp_kernel: true
lora_o_kernel: true
lora_qkv_kernel: true
lora_r: 32
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 0.1
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
output_dir: ./outputs/qwen-sft-pirate-rrr
plugins:
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
sample_packing: true
saves_per_epoch: 2
sequence_len: 4096
warmup_steps: 5
xformers_attention: true

See axolotl config

axolotl version: 0.18.0

adapter: qlora
base_model: mrcuddle/arcee-fusion-lumaid-12B
bf16: false
chat_template: mistral_v2v3
dataloader_num_workers: 2
dataloader_pin_memory: true
dataloader_prefetch_factor: 8
datasets:
- eot_tokens:
  - <|im_end|>
  field: story
  path: bluuwhale/nsfwstory2
  split: train
  type: completion
embeddings_skip_upcast: true
fp16: true
gradient_accumulation_steps: 1
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
learning_rate: 0.00019
load_in_4bit: true
logging_steps: 1
lora_alpha: 64
lora_mlp_kernel: true
lora_o_kernel: true
lora_qkv_kernel: true
lora_r: 32
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- down_proj
- up_proj
lr_scheduler: cosine
max_grad_norm: 0.1
micro_batch_size: 1
num_epochs: 1
optimizer: paged_adamw_8bit
output_dir: ./outputs/qwen-sft-pirate-rrr
plugins:
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
sample_packing: true
saves_per_epoch: 2
sequence_len: 4096
warmup_steps: 5
xformers_attention: true

outputs/qwen-sft-pirate-rrr

This model is a fine-tuned version of mrcuddle/arcee-fusion-lumaid-12B on the bluuwhale/nsfwstory2 dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.00019
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
training_steps: 25
mixed_precision_training: Native AMP

Training results

Framework versions

PEFT 0.19.1
Transformers 5.14.1
Pytorch 2.12.1+cu130
Datasets 4.8.4
Tokenizers 0.22.2

Downloads last month: 17

Model tree for mrcuddle/lummaid-fusion-14B-lora

Base model

mrcuddle/arcee-fusion-lumaid-12B

Adapter

(1)

this model

mrcuddle
/

lummaid-fusion-14B-lora

outputs/qwen-sft-pirate-rrr

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for mrcuddle/lummaid-fusion-14B-lora

Dataset used to train mrcuddle/lummaid-fusion-14B-lora