Instructions to use NotIsora/Qwen2.5-7B-Chef-VN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NotIsora/Qwen2.5-7B-Chef-VN with Transformers:

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

pipe = pipeline("text-generation", model="NotIsora/Qwen2.5-7B-Chef-VN")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NotIsora/Qwen2.5-7B-Chef-VN")
model = AutoModelForCausalLM.from_pretrained("NotIsora/Qwen2.5-7B-Chef-VN", 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 NotIsora/Qwen2.5-7B-Chef-VN with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NotIsora/Qwen2.5-7B-Chef-VN"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NotIsora/Qwen2.5-7B-Chef-VN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NotIsora/Qwen2.5-7B-Chef-VN

SGLang

How to use NotIsora/Qwen2.5-7B-Chef-VN 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 "NotIsora/Qwen2.5-7B-Chef-VN" \
    --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": "NotIsora/Qwen2.5-7B-Chef-VN",
		"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 "NotIsora/Qwen2.5-7B-Chef-VN" \
        --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": "NotIsora/Qwen2.5-7B-Chef-VN",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NotIsora/Qwen2.5-7B-Chef-VN with Docker Model Runner:
```
docker model run hf.co/NotIsora/Qwen2.5-7B-Chef-VN
```

NotIsora commited on Jun 24

Commit

bbcf245

verified ·

1 Parent(s): 82a2bcb

Update README.md

Browse files

Files changed (1) hide show

README.md +43 -1

README.md CHANGED Viewed

@@ -48,6 +48,9 @@ The model should not be used for:
 - Generating harmful, toxic, or unsafe content.
 - Tasks entirely unrelated to food, cooking, or culinary arts (its performance may degrade outside its specialized domain).
 ## Bias, Risks, and Limitations
 While the model generates detailed recipes, cooking involves physical safety (e.g., using knives, handling hot surfaces, food safety/allergies). Users should exercise common sense and verify food safety standards independently. The model may occasionally hallucinate ingredients or steps that do not perfectly align with traditional recipes.
@@ -89,4 +92,43 @@ with torch.inference_mode():
     )
 response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
-print(response)

 - Generating harmful, toxic, or unsafe content.
 - Tasks entirely unrelated to food, cooking, or culinary arts (its performance may degrade outside its specialized domain).
+## If you want to train by yourself
 ## Bias, Risks, and Limitations
 While the model generates detailed recipes, cooking involves physical safety (e.g., using knives, handling hot surfaces, food safety/allergies). Users should exercise common sense and verify food safety standards independently. The model may occasionally hallucinate ingredients or steps that do not perfectly align with traditional recipes.
     )
 response = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
+print(response)
+```
+## Training Details
+### Training Data
+- The model was trained on a processed subset of the AkashPS11/recipes_data_food.com dataset. The data was filtered, parsed, and converted into ChatML format to simulate a user asking for a recipe and a chef responding with structured instructions.
+### Training Procedure
+- The model was trained using parameter-efficient fine-tuning (QLoRA) to optimize VRAM usage while maintaining performance.
+### Training Hyperparameters
+- Training regime: bf16 mixed precision
+- Epochs: 6
+- Max Sequence Length: 1024
+- Per-device Batch Size: 2
+- Gradient Accumulation Steps: 4
+- Optimizer: paged_adamw_8bit
+- Learning Rate: 5e-5
+- Learning Rate Scheduler: Cosine
+- Warmup Ratio: 0.1
+- LoRA Rank (r): 16
+- LoRA Alpha: 32
+## Technical Specifications
+### Compute Infrastructure:
+- The model was trained on Google Colab.
+## Hardware:
+- GPU: 1x NVIDIA L4 / T4 Tensor Core GPU
+### Software:
+- PyTorch
+- Transformers
+- PEFT
+TRL
+- BitsAndBytes
+- FlashAttention / SDPA
+Model Card Contact
+For any questions, issues, or collaborations, feel free to reach out via Hugging Face.