Instructions to use ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill with Transformers:

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

pipe = pipeline("text-generation", model="ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill")
model = AutoModelForCausalLM.from_pretrained("ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill")
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 ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill

SGLang

How to use ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill 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 "ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill" \
    --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": "ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill",
		"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 "ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill" \
        --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": "ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill with Docker Model Runner:
```
docker model run hf.co/ChenDRAG/Qwen2.5-1.5B-Open-R1-Distill
```

ChenDRAG commited on Feb 17, 2025

Commit

1735024

verified ·

1 Parent(s): 790ffd7

Model save

Browse files

Files changed (7) hide show

README.md +2 -2
all_results.json +7 -6
model.safetensors +1 -1
tokenizer.json +2 -2
train_results.json +7 -6
trainer_state.json +15 -17
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -27,14 +27,14 @@ 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/noteam2235/huggingface/runs/4xsgt4nu)
 This model was trained with SFT.
 ### Framework versions
-- TRL: 0.16.0.dev0
 - Transformers: 4.49.0.dev0
 - Pytorch: 2.5.1
 - Datasets: 3.3.0

 ## 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/noteam2235/huggingface/runs/0rzfbsdx)
 This model was trained with SFT.
 ### Framework versions
+- TRL: 0.14.0
 - Transformers: 4.49.0.dev0
 - Pytorch: 2.5.1
 - Datasets: 3.3.0

all_results.json CHANGED Viewed

@@ -1,8 +1,9 @@
 {
-    "total_flos": 1338922500096.0,
-    "train_loss": 0.8787662982940674,
-    "train_runtime": 52.0164,
-    "train_samples": 300,
-    "train_samples_per_second": 8.44,
-    "train_steps_per_second": 0.115
 }

 {
+    "epoch": 1.0,
+    "total_flos": 1713227169792.0,
+    "train_loss": 0.8339962363243103,
+    "train_runtime": 79.6006,
+    "train_samples": 512,
+    "train_samples_per_second": 6.432,
+    "train_steps_per_second": 0.101
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d728507d2aa4a648f418b5491e02e84a26af476918a8e9218e9cb369ea3569b
 size 3087467144

 version https://git-lfs.github.com/spec/v1
+oid sha256:91e0928e844a28ce46c96756c86abe3dd4866b9e10eeb84b47b40de7ebd7a00e
 size 3087467144

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896

 version https://git-lfs.github.com/spec/v1
+oid sha256:83396048d512ec1f3178af0d7c1f79a226bba041822614b0e26a4fd2d4b55bf7
+size 11421995

train_results.json CHANGED Viewed

@@ -1,8 +1,9 @@
 {
-    "total_flos": 1338922500096.0,
-    "train_loss": 0.8787662982940674,
-    "train_runtime": 52.0164,
-    "train_samples": 300,
-    "train_samples_per_second": 8.44,
-    "train_steps_per_second": 0.115
 }

 {
+    "epoch": 1.0,
+    "total_flos": 1713227169792.0,
+    "train_loss": 0.8339962363243103,
+    "train_runtime": 79.6006,
+    "train_samples": 512,
+    "train_samples_per_second": 6.432,
+    "train_steps_per_second": 0.101
 }

trainer_state.json CHANGED Viewed

@@ -1,34 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8727272727272727,
   "eval_steps": 100,
-  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.7272727272727273,
-      "grad_norm": 1.3501643358314308,
-      "learning_rate": 1.9098300562505266e-06,
-      "loss": 0.8944,
-      "mean_token_accuracy": 0.7577449153561558,
       "step": 5
     },
     {
-      "epoch": 0.8727272727272727,
-      "mean_token_accuracy": 0.7622872596745417,
-      "step": 6,
-      "total_flos": 1338922500096.0,
-      "train_loss": 0.8787662982940674,
-      "train_runtime": 52.0164,
-      "train_samples_per_second": 8.44,
-      "train_steps_per_second": 0.115
     }
   ],
   "logging_steps": 5,
-  "max_steps": 6,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -44,7 +42,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1338922500096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 1.0,
   "eval_steps": 100,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 0.625,
+      "grad_norm": 1.2765480627259704,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 0.846,
       "step": 5
     },
     {
+      "epoch": 1.0,
+      "step": 8,
+      "total_flos": 1713227169792.0,
+      "train_loss": 0.8339962363243103,
+      "train_runtime": 79.6006,
+      "train_samples_per_second": 6.432,
+      "train_steps_per_second": 0.101
     }
   ],
   "logging_steps": 5,
+  "max_steps": 8,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
       "attributes": {}
     }
   },
+  "total_flos": 1713227169792.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb35b2251125d46ac633df88868293fe4cfef8f450e9b8b8d0d500ffe8c97d6
 size 7416

 version https://git-lfs.github.com/spec/v1
+oid sha256:0e2b8214a009a973ecaf8845b622ee7cda8a7f25278a76831680805084cf5721
 size 7416