Instructions to use HoangHa/Pensez-v0.1-e5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HoangHa/Pensez-v0.1-e5 with Transformers:

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

pipe = pipeline("text-generation", model="HoangHa/Pensez-v0.1-e5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("HoangHa/Pensez-v0.1-e5")
model = AutoModelForMultimodalLM.from_pretrained("HoangHa/Pensez-v0.1-e5")
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 HoangHa/Pensez-v0.1-e5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HoangHa/Pensez-v0.1-e5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HoangHa/Pensez-v0.1-e5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HoangHa/Pensez-v0.1-e5

SGLang

How to use HoangHa/Pensez-v0.1-e5 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 "HoangHa/Pensez-v0.1-e5" \
    --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": "HoangHa/Pensez-v0.1-e5",
		"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 "HoangHa/Pensez-v0.1-e5" \
        --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": "HoangHa/Pensez-v0.1-e5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HoangHa/Pensez-v0.1-e5 with Docker Model Runner:
```
docker model run hf.co/HoangHa/Pensez-v0.1-e5
```

HoangHa

nielsr HF Staff commited on Apr 17, 2025

Commit

1d9676b

verified ·

1 Parent(s): 27eeeb0

Add pipeline tag and paper link (#1)

Browse files

- Add pipeline tag and paper link (07c04b88480f310b9a91261ff24d30565674e057)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +10 -7

README.md CHANGED Viewed

@@ -1,15 +1,17 @@
 ---
-library_name: transformers
-license: apache-2.0
 datasets:
 - HoangHa/Pensez-v0.1
 language:
 - en
 - fr
-base_model:
-- Qwen/Qwen2.5-7B-Instruct
 ---
 <div align="center">
 # Pensez: Less Data, Better Reasoning – Rethinking French LLM
@@ -23,7 +25,7 @@ base_model:
 ## About
-Paper: [Pensez: Less Data, Better Reasoning - Rethinking French LLM](https://arxiv.org/abs/2503.13661)
 Pensez is a bilingual (French-English) reasoning model designed to maximize efficiency with significantly reduced training data. The model leverages a curated dataset focusing on daily reasoning tasks and scientific questions to enhance performance.
@@ -149,7 +151,7 @@ More details: [Training Config](https://huggingface.co/HoangHa/Pensez-v0.1-e5/bl
       year={2025},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
-      url={},
 }
 ```
@@ -165,4 +167,5 @@ More details: [Training Config](https://huggingface.co/HoangHa/Pensez-v0.1-e5/bl
 - [Deepspeed](https://github.com/deepspeedai/DeepSpeed)
 - [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness)
 - [Hyperbolic](https://hyperbolic.xyz/)
-- [Modal](https://modal.com/)

 ---
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
 datasets:
 - HoangHa/Pensez-v0.1
 language:
 - en
 - fr
+library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 ---
+```markdown
 <div align="center">
 # Pensez: Less Data, Better Reasoning – Rethinking French LLM
 ## About
+Paper: [Pensez: Less Data, Better Reasoning - Rethinking French LLM](https://huggingface.co/papers/2503.13661)
 Pensez is a bilingual (French-English) reasoning model designed to maximize efficiency with significantly reduced training data. The model leverages a curated dataset focusing on daily reasoning tasks and scientific questions to enhance performance.
       year={2025},
       archivePrefix={arXiv},
       primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2503.13661},
 }
 ```
 - [Deepspeed](https://github.com/deepspeedai/DeepSpeed)
 - [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness)
 - [Hyperbolic](https://hyperbolic.xyz/)
+- [Modal](https://modal.com/)
+```