Instructions to use LoudAI/Mistral-7B-Instruct-SQL-ian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoudAI/Mistral-7B-Instruct-SQL-ian with Transformers:

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

pipe = pipeline("text-generation", model="LoudAI/Mistral-7B-Instruct-SQL-ian")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LoudAI/Mistral-7B-Instruct-SQL-ian")
model = AutoModelForCausalLM.from_pretrained("LoudAI/Mistral-7B-Instruct-SQL-ian", 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 LoudAI/Mistral-7B-Instruct-SQL-ian with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LoudAI/Mistral-7B-Instruct-SQL-ian"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoudAI/Mistral-7B-Instruct-SQL-ian",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LoudAI/Mistral-7B-Instruct-SQL-ian

SGLang

How to use LoudAI/Mistral-7B-Instruct-SQL-ian 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 "LoudAI/Mistral-7B-Instruct-SQL-ian" \
    --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": "LoudAI/Mistral-7B-Instruct-SQL-ian",
		"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 "LoudAI/Mistral-7B-Instruct-SQL-ian" \
        --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": "LoudAI/Mistral-7B-Instruct-SQL-ian",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LoudAI/Mistral-7B-Instruct-SQL-ian with Docker Model Runner:
```
docker model run hf.co/LoudAI/Mistral-7B-Instruct-SQL-ian
```

kubwa(LoudAI) commited on Jun 17, 2024

Commit

59dbaf0

verified ·

1 Parent(s): 1686712

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -2

README.md CHANGED Viewed

@@ -15,11 +15,16 @@ This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3. https:
 - **Developed by:** kubwa
 - **Base Model Name:** mistralai/Mistral-7B-Instruct-v0.3
 - **Base Model URL:** [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
 - **Dataset Name:** gretelai/synthetic_text_to_sql
 - **Dataset URL:** [synthetic_text_to_sql](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql)
 - **Dataset Description:** gretelai/synthetic_text_to_sql is a rich dataset of high quality synthetic Text-to-SQL samples, designed and generated using Gretel Navigator, and released under Apache 2.0.
-- **License:** Apache-2.0
--
 ## Prompt Template
 ```
@@ -91,3 +96,8 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
     This result shows that John Doe sold a total of 270 cubic units of timber, while Jane Smith sold 180 cubic units. The result is sorted by the total volume in descending order.
   ```

 - **Developed by:** kubwa
 - **Base Model Name:** mistralai/Mistral-7B-Instruct-v0.3
 - **Base Model URL:** [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
+- **Base Model Description:** The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.
+  Mistral-7B-v0.3 has the following changes compared to Mistral-7B-v0.2
+  - Extended vocabulary to 32768
+  - Supports v3 Tokenizer
+  - Supports function calling
 - **Dataset Name:** gretelai/synthetic_text_to_sql
 - **Dataset URL:** [synthetic_text_to_sql](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql)
 - **Dataset Description:** gretelai/synthetic_text_to_sql is a rich dataset of high quality synthetic Text-to-SQL samples, designed and generated using Gretel Navigator, and released under Apache 2.0.
 ## Prompt Template
 ```
     This result shows that John Doe sold a total of 270 cubic units of timber, while Jane Smith sold 180 cubic units. The result is sorted by the total volume in descending order.
   ```
+## Hardware and Software
+- **Training Hardware:** 4 Tesla V100-PCIE-32GB GPUs
+## License
+- Apache-2.0