Instructions to use autoprogrammer/dream_rcr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use autoprogrammer/dream_rcr with Transformers:

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

pipe = pipeline("text-generation", model="autoprogrammer/dream_rcr", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("autoprogrammer/dream_rcr", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use autoprogrammer/dream_rcr with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/autoprogrammer/dream_rcr

SGLang

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

Docker Model Runner
How to use autoprogrammer/dream_rcr with Docker Model Runner:
```
docker model run hf.co/autoprogrammer/dream_rcr
```

autoprogrammer commited on Sep 24, 2025

Commit

24e35c2

verified ·

1 Parent(s): 9384b5d

Update generation_utils.py

Browse files

Files changed (1) hide show

generation_utils.py +1 -1

generation_utils.py CHANGED Viewed

@@ -171,7 +171,7 @@ class DreamGenerationMixin:
         total_steps: int,
         s: torch.Tensor,
         t: torch.Tensor,
-        ema_beta: float = 0.8            # EMA 平滑系数（越大越稳定）
     ):
         """
         策略要点（接近 vanilla）：

         total_steps: int,
         s: torch.Tensor,
         t: torch.Tensor,
+        ema_beta: float = 0.95            # EMA 平滑系数（越大越稳定）
     ):
         """
         策略要点（接近 vanilla）：