Instructions to use XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy with Transformers:

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

pipe = pipeline("text-generation", model="XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy")
model = AutoModelForCausalLM.from_pretrained("XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy")
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

vLLM

How to use XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy

SGLang

How to use XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy 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 "XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy" \
    --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": "XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy",
		"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 "XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy" \
        --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": "XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy with Docker Model Runner:
```
docker model run hf.co/XeAI/LLaMa_3.2_3B_Instruct_Text2SQL_Legacy
```

ZhafranR commited on Nov 7, 2024

Commit

70faabb

verified ·

1 Parent(s): b00b0fc

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -21,8 +21,8 @@ This is a fine-tuned version of LLaMA 3.2 3B Instruct model, specifically optimi
 - **Finetuned from model:** LLaMA 3.2 3B Instruct
 ### Model Sources
-- **Repository:** https://wandb.ai/zhafranr/LLaMA_3-2_3B_Instruct_FineTune_Text2SQL
-- **Dataset:** https://huggingface.co/datasets/gretelai/synthetic_text_to_sql
 ## How to Get Started with the Model
@@ -166,7 +166,7 @@ The model is designed for converting natural language questions into SQL queries
 ## Training Details
 ### Training Data
-- Dataset: gretelai/synthetic_text_to_sql
 - Data preprocessing: Standard text-to-SQL formatting
 ### Training Procedure
@@ -208,7 +208,7 @@ The model's performance was tracked using several key metrics:
 - **Hardware Type:** NVIDIA H100 GPU
 - **Hours used:** ~6 hours
-- **Training Location:** [User to specify]
 ## Technical Specifications

 - **Finetuned from model:** LLaMA 3.2 3B Instruct
 ### Model Sources
+- **Repository:** [LLaMA 3.2 3B Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
+- **Dataset:** [Synthethic Text2SQL)](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql)
 ## How to Get Started with the Model
 ## Training Details
 ### Training Data
+- Dataset: [Synthethic Text2SQL)](https://huggingface.co/datasets/gretelai/synthetic_text_to_sql)
 - Data preprocessing: Standard text-to-SQL formatting
 ### Training Procedure
 - **Hardware Type:** NVIDIA H100 GPU
 - **Hours used:** ~6 hours
+- **Training Location:** [www.runpod.io](GPUaaS)
 ## Technical Specifications