Instructions to use flammenai/flammen15X-mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flammenai/flammen15X-mistral-7B with Transformers:

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

pipe = pipeline("text-generation", model="flammenai/flammen15X-mistral-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flammenai/flammen15X-mistral-7B")
model = AutoModelForCausalLM.from_pretrained("flammenai/flammen15X-mistral-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flammenai/flammen15X-mistral-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flammenai/flammen15X-mistral-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flammenai/flammen15X-mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flammenai/flammen15X-mistral-7B

SGLang

How to use flammenai/flammen15X-mistral-7B 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 "flammenai/flammen15X-mistral-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flammenai/flammen15X-mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "flammenai/flammen15X-mistral-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flammenai/flammen15X-mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flammenai/flammen15X-mistral-7B with Docker Model Runner:
```
docker model run hf.co/flammenai/flammen15X-mistral-7B
```

flammen15X-mistral-7B / README.md

nbeerbower

Update README.md

7d65d1d verified over 2 years ago

preview code

Raw

History Blame Contribute Delete

2.34 kB

	---
	library_name: transformers
	license: apache-2.0
	base_model:
	- nbeerbower/flammen15-gutenberg-DPO-v1-7B
	datasets:
	- chargoddard/chai-dpo
	---

	![image/png](https://huggingface.co/nbeerbower/flammen13X-mistral-7B/resolve/main/flammen13x.png)

	# flammen15X-mistral-7B

	A Mistral 7B LLM built from merging pretrained models and finetuning on [Jon Durbin](https://huggingface.co/jondurbin)'s [Gutenberg DPO set](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) and [Charles Goddard](https://huggingface.co/chargoddard)'s [Chai DPO set](https://huggingface.co/datasets/chargoddard/chai-dpo).
	Flammen specializes in exceptional character roleplay, creative writing, and general intelligence

	### Method

	Finetuned using an A100 on Google Colab. 🙏

	[Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) - [Maxime Labonne](https://huggingface.co/mlabonne)

	### Configuration

	LoRA, model, and training settings:

	```python
	# LoRA configuration
	peft_config = LoraConfig(
	r=16,
	lora_alpha=16,
	lora_dropout=0.05,
	bias="none",
	task_type="CAUSAL_LM",
	target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']
	)

	# Model to fine-tune
	model = AutoModelForCausalLM.from_pretrained(
	model_name,
	torch_dtype=torch.bfloat16,
	load_in_4bit=True
	)
	model.config.use_cache = False

	# Reference model
	ref_model = AutoModelForCausalLM.from_pretrained(
	model_name,
	torch_dtype=torch.bfloat16,
	load_in_4bit=True
	)

	# Training arguments
	training_args = TrainingArguments(
	per_device_train_batch_size=2,
	gradient_accumulation_steps=2,
	gradient_checkpointing=True,
	learning_rate=2e-5,
	lr_scheduler_type="cosine",
	max_steps=200,
	save_strategy="no",
	logging_steps=1,
	output_dir=new_model,
	optim="paged_adamw_32bit",
	warmup_steps=100,
	bf16=True,
	report_to="wandb",
	)

	# Create DPO trainer
	dpo_trainer = DPOTrainer(
	model,
	ref_model,
	args=training_args,
	train_dataset=dataset,
	tokenizer=tokenizer,
	peft_config=peft_config,
	beta=0.1,
	max_prompt_length=1024,
	max_length=1536,
	force_use_ref_model=True
	)

	# Fine-tune model with DPO
	dpo_trainer.train()
	```