Instructions to use PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL with Transformers:

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

pipe = pipeline("image-text-to-text", model="PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-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("PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL")
model = AutoModelForMultimodalLM.from_pretrained("PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-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 PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-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": "PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL

SGLang

How to use PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-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 "PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-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": "PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-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": "PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL with Docker Model Runner:
```
docker model run hf.co/PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-RL
```

Qwen3.5-0.8B-Reverse-Text-RL

File size: 1,600 Bytes

b83434b
 
 
 
 
 
 
 
 
 
 
 
 
b0e7cfd
b83434b
 
 
b0e7cfd
b83434b
 
 
 
b0e7cfd

---
license: apache-2.0
base_model:
- PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-SFT
library_name: transformers
tags:
- prime-rl
- ci
---

# Qwen3.5-0.8B-Reverse-Text-RL

A short RL fine-tune of [`PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-SFT`](https://huggingface.co/PrimeIntellect/Qwen3.5-0.8B-Reverse-Text-SFT) on the `reverse-text` environment with [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl).
It is meant as the frozen teacher / sampler for the prime-rl CI tests of on-policy distillation and RL-SFT once they move to Qwen3.5 (today they use `PrimeIntellect/Qwen3-0.6B-Reverse-Text-RL`). It is not meant for general use.

## Recipe
- Code: prime-rl commit [`21814b401`](https://github.com/PrimeIntellect-ai/prime-rl/commit/21814b401e29240e8ca4f161dafa0bba6d1425ba).
- Config: `examples/basic/reverse-text/rl.toml` at that commit with `model.name` = the SFT checkpoint and `orchestrator.renderer.name = "qwen3.5"`: 20 steps, 8 prompts x 16 rollouts (batch 128), 128 max tokens, lr 3e-6, 1 inference + 1 trainer H200, NCCL weight broadcast.

## Numbers
- Train reward per step: 0.30, 0.30, 0.30, 0.32, 0.36, 0.33, 0.35, 0.34, 0.35, 0.35, 0.37, 0.40, 0.37, 0.36, 0.39, 0.38, 0.41, 0.43, 0.41, 0.42.
- `reverse-text` eval reward (256 prompts, temperature 1): step 0: 0.3086, step 5: 0.3543, step 10: 0.3967, step 15: 0.4027, step 20: 0.4077.

## Caveat
On Qwen3.5-0.8B, prime-rl RL currently shows a much higher trainer/inference mismatch KL (0.01-0.1 per step) than on Qwen3-0.6B (about 0.002) with the same recipe, and learning stalls after about 20 steps. This is under investigation.