Instructions to use DeepMount00/Qwen2-1.5B-Ita with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepMount00/Qwen2-1.5B-Ita with Transformers:

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

pipe = pipeline("text-generation", model="DeepMount00/Qwen2-1.5B-Ita")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepMount00/Qwen2-1.5B-Ita")
model = AutoModelForCausalLM.from_pretrained("DeepMount00/Qwen2-1.5B-Ita")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DeepMount00/Qwen2-1.5B-Ita with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepMount00/Qwen2-1.5B-Ita"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepMount00/Qwen2-1.5B-Ita",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeepMount00/Qwen2-1.5B-Ita

SGLang

How to use DeepMount00/Qwen2-1.5B-Ita 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 "DeepMount00/Qwen2-1.5B-Ita" \
    --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": "DeepMount00/Qwen2-1.5B-Ita",
		"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 "DeepMount00/Qwen2-1.5B-Ita" \
        --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": "DeepMount00/Qwen2-1.5B-Ita",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeepMount00/Qwen2-1.5B-Ita with Docker Model Runner:
```
docker model run hf.co/DeepMount00/Qwen2-1.5B-Ita
```

Fine-tuning this model

by danielus - opened Jul 9, 2024

Discussion

danielus

Jul 9, 2024

Hi! I want to approach the world of language models a little more seriously, so I would like to try finetuning a model. Not experience with this, would you be able to tell me if this model is finetunable further? Or since you have already done your finetuning I might have poor results?

I would like to try finetuning it on a specific task and I have a few hundred prompt-response examples.

DeepMount00

Owner Jul 9, 2024

Hi! Absolutely, you can further finetune this model for a specific task. I am actually updating the model in a few hours to enhance its understanding of Italian, logical reasoning, and critical thinking. Finetuning on your specific task with a few hundred prompt-response examples should yield decent results, especially after the upcoming updates. Let me know if you need any assistance with the finetuning process!

danielus

Jul 9, 2024

I will look forward to the update. Thank you very much <3

Regarding training, I currently have a laptop with a rtx 2060 6GB of VRAM, but according to the huggingface space Can-You-Run-It's not enough to train it in fp16, does training it with lower accuracies worsen the quality of training?

I could potentially use a VM on google cloud with a Nvidia L4, how long more or less does it take to finetuning?

Doing rough calculations each prompt-response pair is about 2k tokens, so if I were to have about 300 examples that's 600k tokens

I would prefer to train it on my laptop, since I can take my time and experiment more comfortably. What do you think?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment