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

Libraries

How to use tamilanda/my-sql-model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-Instruct-hf")
model = PeftModel.from_pretrained(base_model, "tamilanda/my-sql-model")

Transformers

How to use tamilanda/my-sql-model with Transformers:

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

pipe = pipeline("text-generation", model="tamilanda/my-sql-model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tamilanda/my-sql-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tamilanda/my-sql-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tamilanda/my-sql-model

SGLang

How to use tamilanda/my-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 "tamilanda/my-sql-model" \
    --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": "tamilanda/my-sql-model",
		"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 "tamilanda/my-sql-model" \
        --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": "tamilanda/my-sql-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

my-sql-model

File size: 2,472 Bytes

bd5e611

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 10.467041015625,
      "learning_rate": 4.6200000000000005e-05,
      "loss": 2.8162,
      "step": 20
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.9829273223876953,
      "learning_rate": 4.22e-05,
      "loss": 1.9308,
      "step": 40
    },
    {
      "epoch": 0.24,
      "grad_norm": 4.000159740447998,
      "learning_rate": 3.82e-05,
      "loss": 1.6849,
      "step": 60
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.9223499298095703,
      "learning_rate": 3.4200000000000005e-05,
      "loss": 1.5359,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.8478671312332153,
      "learning_rate": 3.02e-05,
      "loss": 1.571,
      "step": 100
    },
    {
      "epoch": 0.48,
      "grad_norm": 2.243217945098877,
      "learning_rate": 2.6200000000000003e-05,
      "loss": 1.5199,
      "step": 120
    },
    {
      "epoch": 0.56,
      "grad_norm": 2.793548345565796,
      "learning_rate": 2.22e-05,
      "loss": 1.5036,
      "step": 140
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.5502959489822388,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 1.4294,
      "step": 160
    },
    {
      "epoch": 0.72,
      "grad_norm": 5.679831504821777,
      "learning_rate": 1.42e-05,
      "loss": 1.4503,
      "step": 180
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.3757414817810059,
      "learning_rate": 1.02e-05,
      "loss": 1.4753,
      "step": 200
    },
    {
      "epoch": 0.8,
      "eval_loss": 1.129705786705017,
      "eval_runtime": 1533.624,
      "eval_samples_per_second": 0.652,
      "eval_steps_per_second": 0.326,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.2517969149952e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}