Instructions to use kirankotha/mistral7b-sql-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kirankotha/mistral7b-sql-model with Transformers:

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

pipe = pipeline("text-generation", model="kirankotha/mistral7b-sql-model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kirankotha/mistral7b-sql-model")
model = AutoModelForCausalLM.from_pretrained("kirankotha/mistral7b-sql-model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kirankotha/mistral7b-sql-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kirankotha/mistral7b-sql-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kirankotha/mistral7b-sql-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kirankotha/mistral7b-sql-model

SGLang

How to use kirankotha/mistral7b-sql-model 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 "kirankotha/mistral7b-sql-model" \
    --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": "kirankotha/mistral7b-sql-model",
		"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 "kirankotha/mistral7b-sql-model" \
        --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": "kirankotha/mistral7b-sql-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kirankotha/mistral7b-sql-model with Docker Model Runner:
```
docker model run hf.co/kirankotha/mistral7b-sql-model
```

kirankotha commited on Oct 11, 2025

Commit

aac8308

verified ·

1 Parent(s): 9f2d1c0

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +39 -10

README.md CHANGED Viewed

@@ -1,15 +1,44 @@
-# Mistral-7B SQL Model (Saved)
-This folder contains the tokenizer and either full model weights or LoRA adapters.
-## Loading
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
 import torch
-model_path = '/content/drive/MyDrive/mistral7b_sql_model'
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=torch.bfloat16, device_map='auto')
-```

+---
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- mistral
+- text-to-sql
+- sql
+language:
+- en
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+---
+# Mistral-7B SQL (fine-tuned)
+Fine-tuned Mistral-7B for Text-to-SQL on `b-mc2/sql-create-context`.
+## Usage (Transformers)
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
+model_id = "kirankotha/mistral7b-sql-model"
+tok = AutoTokenizer.from_pretrained(model_id)
+mdl = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
+prompt = (
+    "You are a text-to-SQL model.
+"
+    "### Input:
+"
+    "Which product has the highest price?
+"
+    "### Context:
+"
+    "CREATE TABLE products (id INTEGER, name TEXT, price REAL)
+"
+    "### Response:
+"
+)
+ids = tok(prompt, return_tensors="pt").to(mdl.device)
+out = mdl.generate(**ids, max_new_tokens=100, do_sample=False, pad_token_id=tok.pad_token_id)
+print(tok.decode(out[0], skip_special_tokens=True))