Instructions to use leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic with Transformers:

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

pipe = pipeline("text-generation", model="leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic")
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-1.5B-GSPO-Basic")
model = AutoModelForCausalLM.from_pretrained("leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic", 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-1.5B-GSPO-Basic 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-1.5B-GSPO-Basic"
# 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-1.5B-GSPO-Basic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic

SGLang

How to use leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic 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-1.5B-GSPO-Basic" \
    --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-1.5B-GSPO-Basic",
		"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-1.5B-GSPO-Basic" \
        --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-1.5B-GSPO-Basic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic with Docker Model Runner:
```
docker model run hf.co/leonMW/DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic
```

leonMW commited on Sep 4, 2025

Commit

55ecd98

verified ·

1 Parent(s): ede287f

Merged basemodel Qwen2ForCausalLM(

Browse files

(model): Qwen2Model(
(embed_tokens): Embedding(151936, 1536)
(layers): ModuleList(
(0-27): 28 x Qwen2DecoderLayer(
(self_attn): Qwen2Attention(
(q_proj): Linear(in_features=1536, out_features=1536, bias=True)
(k_proj): Linear(in_features=1536, out_features=256, bias=True)
(v_proj): Linear(in_features=1536, out_features=256, bias=True)
(o_proj): Linear(in_features=1536, out_features=1536, bias=False)
)
(mlp): Qwen2MLP(
(gate_proj): Linear(in_features=1536, out_features=8960, bias=False)
(up_proj): Linear(in_features=1536, out_features=8960, bias=False)
(down_proj): Linear(in_features=8960, out_features=1536, bias=False)
(act_fn): SiLU()
)
(input_layernorm): Qwen2RMSNorm((1536,), eps=1e-06)
(post_attention_layernorm): Qwen2RMSNorm((1536,), eps=1e-06)
)
)
(norm): Qwen2RMSNorm((1536,), eps=1e-06)
(rotary_emb): Qwen2RotaryEmbedding()
)
(lm_head): Linear(in_features=1536, out_features=151936, bias=False)
) with LoRA adapter leonMW/DeepSeek-R1-Distill-Qwen-1.5B-LORA-GSPO-Basic using revision main

Files changed (3) hide show

config.json +2 -2
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -4,6 +4,7 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
   "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
@@ -50,8 +51,7 @@
   "rope_theta": 10000,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.4",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
+  "dtype": "bfloat16",
   "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1536,
   "rope_theta": 10000,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "transformers_version": "4.56.0",
   "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,

generation_config.json CHANGED Viewed

@@ -5,5 +5,5 @@
   "eos_token_id": 151643,
   "temperature": 0.6,
   "top_p": 0.95,
-  "transformers_version": "4.55.4"
 }

   "eos_token_id": 151643,
   "temperature": 0.6,
   "top_p": 0.95,
+  "transformers_version": "4.56.0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9c77c3fdf9e370011657943233f1c1587683ab49afbdc1f65a23d80be19dc3
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:0f463ca8c6a75e4a6cacf4f64f0ca918d583501151c9fda98c0a3e83e0bba45d
 size 3554214752