Instructions to use Dat1710/countdown-grpo-qwen2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dat1710/countdown-grpo-qwen2 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Math-1.5B")
model = PeftModel.from_pretrained(base_model, "Dat1710/countdown-grpo-qwen2")

Transformers

How to use Dat1710/countdown-grpo-qwen2 with Transformers:

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

pipe = pipeline("text-generation", model="Dat1710/countdown-grpo-qwen2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Dat1710/countdown-grpo-qwen2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dat1710/countdown-grpo-qwen2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dat1710/countdown-grpo-qwen2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dat1710/countdown-grpo-qwen2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dat1710/countdown-grpo-qwen2

SGLang

How to use Dat1710/countdown-grpo-qwen2 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 "Dat1710/countdown-grpo-qwen2" \
    --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": "Dat1710/countdown-grpo-qwen2",
		"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 "Dat1710/countdown-grpo-qwen2" \
        --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": "Dat1710/countdown-grpo-qwen2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dat1710/countdown-grpo-qwen2 with Docker Model Runner:
```
docker model run hf.co/Dat1710/countdown-grpo-qwen2
```

Dat1710 commited on Jan 30

Commit

98f2961

verified ·

1 Parent(s): 2ac4c5d

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +2 -2
tokenizer_config.json +0 -2

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
-size 11422063

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

tokenizer_config.json CHANGED Viewed

@@ -201,9 +201,7 @@
   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
-  "padding_side": "left",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
-  "truncation_side": "left",
   "unk_token": null
 }

   "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
 }