Instructions to use Qiskit/Qwen2.5-Coder-14B-Qiskit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qiskit/Qwen2.5-Coder-14B-Qiskit with Transformers:

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

pipe = pipeline("text-generation", model="Qiskit/Qwen2.5-Coder-14B-Qiskit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Qiskit/Qwen2.5-Coder-14B-Qiskit", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Qiskit/Qwen2.5-Coder-14B-Qiskit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qiskit/Qwen2.5-Coder-14B-Qiskit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Qiskit/Qwen2.5-Coder-14B-Qiskit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit

SGLang

How to use Qiskit/Qwen2.5-Coder-14B-Qiskit 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 "Qiskit/Qwen2.5-Coder-14B-Qiskit" \
    --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": "Qiskit/Qwen2.5-Coder-14B-Qiskit",
		"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 "Qiskit/Qwen2.5-Coder-14B-Qiskit" \
        --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": "Qiskit/Qwen2.5-Coder-14B-Qiskit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qiskit/Qwen2.5-Coder-14B-Qiskit with Docker Model Runner:
```
docker model run hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit
```

Update metrics table for new qiskit mistral

by tidealwari - opened Feb 3

base: refs/heads/main

←

from: refs/pr/8

Discussion Files changed

-3

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -116,10 +116,10 @@ We advise adding the `rope_scaling` configuration only when processing long cont
 | **Model** | **QiskitHumanEval-Hard** | **QiskitHumanEval** | **HumanEval** | **ASDiv** | **MathQA** | **SciQ** | **MBPP** | **IFEval** | **CrowsPairs (English)** | **TruthfulQA (MC1 acc)** |
 |-----------|---------------------------|----------------------|---------------|-----------|------------|----------|----------|------------|---------------------------|---------------------------|
-| **qwen2.5-coder-14b-qiskit** | **25.17** | **49.01** | **91.46** | 4.21 | **53.90** | **97.00** | **77.60** | 49.64 | 65.18 | 37.82 |
-| mistral-small-3.2-24b-qiskit | 20.53 | 40.39 | 77.49 | **20.69** | 53.40 | 96.40 | 63.40 | 31.66 | 67.56 | **42.84** |
 | granite-3.3-8b-qiskit | 14.57 | 27.15 | 62.80 | 0.48 | 38.66 | 93.30 | 52.40 | 59.71 | **59.75** | 39.05 |
-| granite-3.2-8b-qiskit | 9.93 | 24.50 | 57.32 | 0.09 | 41.41 | 96.30 | 51.80 | **60.79** | 66.79 | 40.51 |
 *Note: All models listed in the benchmark table were evaluated using their respective system prompt, defined in their Hugging Face model.*

 | **Model** | **QiskitHumanEval-Hard** | **QiskitHumanEval** | **HumanEval** | **ASDiv** | **MathQA** | **SciQ** | **MBPP** | **IFEval** | **CrowsPairs (English)** | **TruthfulQA (MC1 acc)** |
 |-----------|---------------------------|----------------------|---------------|-----------|------------|----------|----------|------------|---------------------------|---------------------------|
+| **qwen2.5-coder-14b-qiskit** | 25.17 | **49.01** | **91.46** | **4.21** | **53.90** | 97.00 | **77.60** | 49.64 | 65.18 | 37.82 |
+| mistral-small-3.2-24b-qiskit | **32.45** | 47.02 | 77.49 | 3.77 | 49.68 | **97.50** | 64.00 | 48.44 | 67.08 | 39.41 |
 | granite-3.3-8b-qiskit | 14.57 | 27.15 | 62.80 | 0.48 | 38.66 | 93.30 | 52.40 | 59.71 | **59.75** | 39.05 |
+| granite-3.2-8b-qiskit | 9.93 | 24.50 | 57.32 | 0.09 | 41.41 | 96.30 | 51.80 | **60.79** | 66.79 | **40.51** |
 *Note: All models listed in the benchmark table were evaluated using their respective system prompt, defined in their Hugging Face model.*