Instructions to use Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc with Transformers:

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

pipe = pipeline("text-generation", model="Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc")
model = AutoModelForCausalLM.from_pretrained("Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc")
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

vLLM

How to use Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc

SGLang

How to use Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc 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 "Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc" \
    --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": "Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc",
		"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 "Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc" \
        --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": "Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc with Docker Model Runner:
```
docker model run hf.co/Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc
```

qwen2.5-coder-14b-instruct-ai-workshop-poc

This model is based on Qwen2.5-Coder-14B-Instruct and was fine-tuned for a focused proof-of-concept AI workshop setting. It is intended as a controlled demonstration model rather than a general-purpose coding release. While the base coding capabilities were preserved, the model was optimized for a narrow workshop scenario and should be evaluated in that context before broader use.

Repository contents

This repository contains the merged 16-bit model weights in Hugging Face safetensors format.

Intended use

This release is intended for controlled demonstration and evaluation scenarios related to the workshop context described above.

Limitations

This is not presented as a default recommendation for everyday software development workflows. It should be assessed in its intended scenario before broader adoption.

Downloads last month: 8

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for Goro64/qwen2.5-coder-14b-instruct-ai-workshop-poc

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-Coder-14B

Finetuned

Qwen/Qwen2.5-Coder-14B-Instruct

Finetuned

(107)

this model