Instructions to use FineEnvs/Qwen3.5-2B-opencode-standalone-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FineEnvs/Qwen3.5-2B-opencode-standalone-RL with Transformers:

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

pipe = pipeline("text-generation", model="FineEnvs/Qwen3.5-2B-opencode-standalone-RL")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("FineEnvs/Qwen3.5-2B-opencode-standalone-RL")
model = AutoModelForMultimodalLM.from_pretrained("FineEnvs/Qwen3.5-2B-opencode-standalone-RL", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FineEnvs/Qwen3.5-2B-opencode-standalone-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FineEnvs/Qwen3.5-2B-opencode-standalone-RL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FineEnvs/Qwen3.5-2B-opencode-standalone-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FineEnvs/Qwen3.5-2B-opencode-standalone-RL

SGLang

How to use FineEnvs/Qwen3.5-2B-opencode-standalone-RL 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 "FineEnvs/Qwen3.5-2B-opencode-standalone-RL" \
    --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": "FineEnvs/Qwen3.5-2B-opencode-standalone-RL",
		"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 "FineEnvs/Qwen3.5-2B-opencode-standalone-RL" \
        --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": "FineEnvs/Qwen3.5-2B-opencode-standalone-RL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FineEnvs/Qwen3.5-2B-opencode-standalone-RL with Docker Model Runner:
```
docker model run hf.co/FineEnvs/Qwen3.5-2B-opencode-standalone-RL
```

AdithyaSK HF Staff commited on 24 days ago

Commit

03d1914

verified ·

1 Parent(s): 8fadc92

Add animated training, evaluation and tool-use curves

Browse files

Files changed (5) hide show

.gitattributes +2 -0
README.md +8 -0
assets/curves.gif +3 -0
assets/curves.json +0 -0
assets/curves.png +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/curves.gif filter=lfs diff=lfs merge=lfs -text
+assets/curves.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -95,6 +95,14 @@ A full fine-tune of [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) fo
 [Article](https://huggingface.co/spaces/AdithyaSK/multi-harness-rl) · [Collection](https://huggingface.co/collections/FineEnvs/multi-harness-rl-6abdfaaa8d74dacd481d5212) · [Evaluation tasks](https://huggingface.co/datasets/FineEnvs/SmolDataEnvs-harbor-test) · [Training dashboard](https://huggingface.co/spaces/FineEnvs/data-agent-training-comparison-trackio)
 ## Training
 TRL Async GRPO with **binary correctness only**, initialized from the base model. All training rollouts use OpenCode. The standalone OpenCode environment runs outside Harbor in Daytona sandboxes.

 [Article](https://huggingface.co/spaces/AdithyaSK/multi-harness-rl) · [Collection](https://huggingface.co/collections/FineEnvs/multi-harness-rl-6abdfaaa8d74dacd481d5212) · [Evaluation tasks](https://huggingface.co/datasets/FineEnvs/SmolDataEnvs-harbor-test) · [Training dashboard](https://huggingface.co/spaces/FineEnvs/data-agent-training-comparison-trackio)
+## Training and evaluation curves
+[![Animated training, pass@1 and tool-use curves through step 1,000](https://huggingface.co/FineEnvs/Qwen3.5-2B-opencode-standalone-RL/resolve/main/assets/curves.gif)](https://huggingface.co/spaces/AdithyaSK/multi-harness-rl)
+Training curves use a trailing 50-step mean (at least 10 observations). Evaluation markers show measured checkpoints; hollow markers indicate incomplete coverage. The tool-use panel shows absolute calls per graded evaluation rollout; this Qwen run used correctness-only rewards.  The animation stops at this revision's step 1,000.
+[Static chart](https://huggingface.co/FineEnvs/Qwen3.5-2B-opencode-standalone-RL/resolve/main/assets/curves.png) · [Plotted data](https://huggingface.co/FineEnvs/Qwen3.5-2B-opencode-standalone-RL/resolve/main/assets/curves.json) · [Interactive article](https://huggingface.co/spaces/AdithyaSK/multi-harness-rl)
 ## Training
 TRL Async GRPO with **binary correctness only**, initialized from the base model. All training rollouts use OpenCode. The standalone OpenCode environment runs outside Harbor in Daytona sandboxes.

assets/curves.gif ADDED Viewed

Git LFS Details

SHA256: f9a4904041067af0ae6495510610b8d6363272dfe614cadb70c7f2a268bfef11
Pointer size: 132 Bytes
Size of remote file: 3.29 MB

assets/curves.json ADDED Viewed

The diff for this file is too large to render. See raw diff

assets/curves.png ADDED Viewed

Git LFS Details

SHA256: 200a4f43bfb19b50a54642f368f72aeff388f5cd3d252d21d6b96b31fc555bab
Pointer size: 131 Bytes
Size of remote file: 156 kB