Instructions to use Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA with Transformers:

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

pipe = pipeline("text-generation", model="Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA")
model = AutoModelForCausalLM.from_pretrained("Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-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 Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-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": "Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA

SGLang

How to use Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-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 "Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-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": "Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-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 "Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-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": "Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA with Docker Model Runner:
```
docker model run hf.co/Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

LoRA fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 targeting all the modules.

Training Hyperparameters

Training regime:

quantization_config = transformers.BitsAndBytesConfig(load_in_4bit=True)

tokenizer = AutoTokenizer.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1", truncation=True, padding=True, padding_side="right")
model = AutoModelForCausalLM.from_pretrained("mistralai/Mixtral-8x7B-Instruct-v0.1", quantization_config=quantization_config)
tokenizer.add_special_tokens({'pad_token': '[PAD]'})

model = prepare_model_for_kbit_training(model)

config = LoraConfig(r = 4, 
                    lora_alpha=4, 
                    target_modules = ["gate", "q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj"], 
                    lora_dropout=0.1
                    )

lora_model = get_peft_model(model, config)

lora_model.print_trainable_parameters()

dataset = load_dataset("Na0s/sft-ready-Text-Generation-Augmented-Data", split="train")

trainer = SFTTrainer(
    model = lora_model,
    tokenizer = tokenizer,
    train_dataset = dataset,
    packing = True,
    args = TrainingArguments(
        per_device_train_batch_size = 1,
        gradient_accumulation_steps = 16,
        group_by_length = True,
        warmup_steps = 5,
        bf16 = True,
        max_steps=10000,
        learning_rate = 2e-4,
        optim = "adamw_8bit",
        weight_decay = 0.01,
        lr_scheduler_type = "cosine",
        seed = 3407,
        eval_strategy="no",
        do_eval=False,
        output_dir = "./outputs",
        push_to_hub=True,
        remove_unused_columns=False,
    )
)

torch.cuda.empty_cache()

trainer.train()

Metrics and results:

Upcoming.

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Technical Specifications

Model Architecture and Objective

The objective of the fine-tuning of this MoE based transformer is to implement the expert pruning detailed in the following paper: A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts