Instructions to use leonMW/DeepSeek-R1-Distill-Qwen-7B-S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leonMW/DeepSeek-R1-Distill-Qwen-7B-S with Transformers:

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

pipe = pipeline("text-generation", model="leonMW/DeepSeek-R1-Distill-Qwen-7B-S")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("leonMW/DeepSeek-R1-Distill-Qwen-7B-S")
model = AutoModelForCausalLM.from_pretrained("leonMW/DeepSeek-R1-Distill-Qwen-7B-S", 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 leonMW/DeepSeek-R1-Distill-Qwen-7B-S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leonMW/DeepSeek-R1-Distill-Qwen-7B-S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leonMW/DeepSeek-R1-Distill-Qwen-7B-S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leonMW/DeepSeek-R1-Distill-Qwen-7B-S

SGLang

How to use leonMW/DeepSeek-R1-Distill-Qwen-7B-S 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 "leonMW/DeepSeek-R1-Distill-Qwen-7B-S" \
    --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": "leonMW/DeepSeek-R1-Distill-Qwen-7B-S",
		"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 "leonMW/DeepSeek-R1-Distill-Qwen-7B-S" \
        --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": "leonMW/DeepSeek-R1-Distill-Qwen-7B-S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use leonMW/DeepSeek-R1-Distill-Qwen-7B-S with Docker Model Runner:
```
docker model run hf.co/leonMW/DeepSeek-R1-Distill-Qwen-7B-S
```

leonMW commited on Sep 23, 2025

Commit

5b27081

verified ·

1 Parent(s): d9ae97c

Training in progress, epoch 1

Browse files

Files changed (8) hide show

README.md +7 -6
config.json +1 -1
model-00001-of-00004.safetensors +1 -1
model-00002-of-00004.safetensors +1 -1
model-00003-of-00004.safetensors +1 -1
model-00004-of-00004.safetensors +1 -1
tokenizer_config.json +0 -4
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,16 +1,17 @@
 ---
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-7B-S
 tags:
 - generated_from_trainer
-- grpo
 - trl
 licence: license
 ---
 # Model Card for DeepSeek-R1-Distill-Qwen-7B-S
-This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -26,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/leonwenderoth-tu-darmstadt/huggingface/runs/3b318nnm)
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
@@ -34,10 +35,10 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 ### Framework versions
 - TRL: 0.23.0
-- Transformers: 4.56.1
 - Pytorch: 2.7.1
-- Datasets: 4.1.0
-- Tokenizers: 0.22.0
 ## Citations

 ---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-7B-S
 tags:
 - generated_from_trainer
 - trl
+- grpo
 licence: license
 ---
 # Model Card for DeepSeek-R1-Distill-Qwen-7B-S
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/leonwenderoth-tu-darmstadt/huggingface/runs/6e7rbl0y)
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 ### Framework versions
 - TRL: 0.23.0
+- Transformers: 4.56.2
 - Pytorch: 2.7.1
+- Datasets: 4.1.1
+- Tokenizers: 0.22.1
 ## Citations

config.json CHANGED Viewed

@@ -52,7 +52,7 @@
   "rope_theta": 10000,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "transformers_version": "4.56.1",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

   "rope_theta": 10000,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

model-00001-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e1554944693ab2c2ee2206298f672ad187461af7273c75a2846dfcfdafc5ce
 size 4877660776

 version https://git-lfs.github.com/spec/v1
+oid sha256:f92e283c68a5aaaec340154b19c5eb47b1af2763d5f8373fb828f2d9e99c090f
 size 4877660776

model-00002-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e7d92b415e20cf4860a58c03441f1d7c36094f14f85e6eb7811b04a6cd4384
 size 4932751008

 version https://git-lfs.github.com/spec/v1
+oid sha256:8071dbd73b597cf546bcc617e1fe0ea63e345ad0ca74131e9edd534f4a7300da
 size 4932751008

model-00003-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6c4440cef95ba260c50cdadcf504608b5be3a974ba61880ebd20438ebb5bc7a
 size 4330865200

 version https://git-lfs.github.com/spec/v1
+oid sha256:e8a082cc033a19c7e743abbe2ebd4d4b964c0a464bf7373434f6c70fc0529581
 size 4330865200

model-00004-of-00004.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73fe97f70c9c92587afcc3726d3718965c64ac523630704c96617a0551c539e2
 size 1089994880

 version https://git-lfs.github.com/spec/v1
+oid sha256:73725f36c100c9544e595c52f70ea3b8b1f2bd2702e6dd05a0cc7cce5cacc4d1
 size 1089994880

tokenizer_config.json CHANGED Viewed

@@ -185,12 +185,8 @@
   "eos_token": "<｜end▁of▁sentence｜>",
   "extra_special_tokens": {},
   "legacy": true,
-  "max_length": null,
   "model_max_length": 16384,
-  "pad_to_multiple_of": null,
   "pad_token": "<｜end▁of▁sentence｜>",
-  "pad_token_type_id": 0,
-  "padding_side": "left",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizerFast",
   "unk_token": null,

   "eos_token": "<｜end▁of▁sentence｜>",
   "extra_special_tokens": {},
   "legacy": true,
   "model_max_length": 16384,
   "pad_token": "<｜end▁of▁sentence｜>",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizerFast",
   "unk_token": null,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:311ddb11cdb2270d9b5f9713aaf543b5aeaa254ca31d6d738d23ad0aaf61d89f
 size 11665

 version https://git-lfs.github.com/spec/v1
+oid sha256:b4c22616f29b6acb0c167ad6cfb8098e01151b4a513cbf44c28513543f5a598c
 size 11665