Instructions to use Ma7ee7/Andgit-0.6B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ma7ee7/Andgit-0.6B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="Ma7ee7/Andgit-0.6B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ma7ee7/Andgit-0.6B-SFT")
model = AutoModelForCausalLM.from_pretrained("Ma7ee7/Andgit-0.6B-SFT", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ma7ee7/Andgit-0.6B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ma7ee7/Andgit-0.6B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ma7ee7/Andgit-0.6B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ma7ee7/Andgit-0.6B-SFT

SGLang

How to use Ma7ee7/Andgit-0.6B-SFT 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 "Ma7ee7/Andgit-0.6B-SFT" \
    --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": "Ma7ee7/Andgit-0.6B-SFT",
		"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 "Ma7ee7/Andgit-0.6B-SFT" \
        --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": "Ma7ee7/Andgit-0.6B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ma7ee7/Andgit-0.6B-SFT with Docker Model Runner:
```
docker model run hf.co/Ma7ee7/Andgit-0.6B-SFT
```

Andgit-0.6B-SFT / validation_metrics.json

Ma7ee7

Upload fine-tuned model and tokenizer

de73bbc verified 4 days ago

Raw History Blame Contribute Delete

456 Bytes

{
  "baseline": {
    "baseline_loss": 1.8666167259216309,
    "baseline_model_preparation_time": 0.0054,
    "baseline_runtime": 38.6136,
    "baseline_samples_per_second": 6.63,
    "baseline_steps_per_second": 6.63
  },
  "best": {
    "best_loss": 1.2588708400726318,
    "best_model_preparation_time": 0.0054,
    "best_runtime": 34.2321,
    "best_samples_per_second": 7.478,
    "best_steps_per_second": 7.478,
    "epoch": 0.22501300856455764
  }
}

	{
	"baseline": {
	"baseline_loss": 1.8666167259216309,
	"baseline_model_preparation_time": 0.0054,
	"baseline_runtime": 38.6136,
	"baseline_samples_per_second": 6.63,
	"baseline_steps_per_second": 6.63
	},
	"best": {
	"best_loss": 1.2588708400726318,
	"best_model_preparation_time": 0.0054,
	"best_runtime": 34.2321,
	"best_samples_per_second": 7.478,
	"best_steps_per_second": 7.478,
	"epoch": 0.22501300856455764
	}
	}