Instructions to use flammenai/Mahou-1.0-mistral-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flammenai/Mahou-1.0-mistral-7B with Transformers:

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

pipe = pipeline("text-generation", model="flammenai/Mahou-1.0-mistral-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flammenai/Mahou-1.0-mistral-7B")
model = AutoModelForCausalLM.from_pretrained("flammenai/Mahou-1.0-mistral-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use flammenai/Mahou-1.0-mistral-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flammenai/Mahou-1.0-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/Mahou-1.0-mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flammenai/Mahou-1.0-mistral-7B

SGLang

How to use flammenai/Mahou-1.0-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/Mahou-1.0-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/Mahou-1.0-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/Mahou-1.0-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/Mahou-1.0-mistral-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flammenai/Mahou-1.0-mistral-7B with Docker Model Runner:
```
docker model run hf.co/flammenai/Mahou-1.0-mistral-7B
```

nbeerbower commited on May 8, 2024

Commit

2b0b547

verified ·

1 Parent(s): 21efb68

Update README.md

Browse files

Files changed (1) hide show

README.md +72 -1

README.md CHANGED Viewed

@@ -6,5 +6,76 @@ base_model:
 datasets:
 - flammenai/FlameMix-DPO-v1
 ---
-# Mahou-1.0-mistral-7B

 datasets:
 - flammenai/FlameMix-DPO-v1
 ---
+![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png)
+# Mahou-1.0-mistral-7B
+Mahou is our attempt to build a production-ready conversational/roleplay LLM.
+Future versions will be released iteratively and finetuned from flammen.ai conversational data.
+NOTE: this model is experimental and currently significantly flawed.
+### 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=4,
+    gradient_accumulation_steps=4,
+    gradient_checkpointing=True,
+    learning_rate=5e-5,
+    lr_scheduler_type="cosine",
+    max_steps=2000,
+    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=2048,
+    max_length=8192,
+    force_use_ref_model=True
+)
+```