Instructions to use Fate-Zero/Archer-Code-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fate-Zero/Archer-Code-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="Fate-Zero/Archer-Code-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fate-Zero/Archer-Code-1.5B")
model = AutoModelForCausalLM.from_pretrained("Fate-Zero/Archer-Code-1.5B")
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

vLLM

How to use Fate-Zero/Archer-Code-1.5B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Fate-Zero/Archer-Code-1.5B

SGLang

How to use Fate-Zero/Archer-Code-1.5B 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 "Fate-Zero/Archer-Code-1.5B" \
    --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": "Fate-Zero/Archer-Code-1.5B",
		"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 "Fate-Zero/Archer-Code-1.5B" \
        --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": "Fate-Zero/Archer-Code-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fate-Zero/Archer-Code-1.5B with Docker Model Runner:
```
docker model run hf.co/Fate-Zero/Archer-Code-1.5B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

✨ Archer

🏹️ Reinforcement Learning for Enhanced Reasoning in LLMs 🎯

Overview

The Archer series focuses on research into RL algorithms and training for medium and small-scale models, aiming to deepen the community's understanding of the fundamental principles of reinforcement learning (RL) on large language models (LLMs). All released content will be comprehensively open-sourced to advance community research development.

_{Archer significantly improves the reasoning performance upon DAPO and outperforms previous 1.5B-level SOTA reasoning models.}

Archer is an open-source initiative enhancing reasoning in large language models through scalable, rule-governed reinforcement learning. We provide full-stack reproducibility including:

Training code and pipelines
Curated datasets
Trained models
Complete training logs

Current Models:

Archer-Code-1.5B - SOTA among similarly-sized models.

Evaluation

We conduct evaluation on both mathematical and coding benchmarks. Due to the high variance of the outputs from reasoning models, we report avg@K (pass@1 performance averaged over K outputs) and pass@K for each benchmark. The detailed results are shown in the table below.

Method	AIME24		AIME25		AMC23		MATH-500		Minerva		Olympiad		Avg.
Method	avg@64	pass@64	avg@64	pass@64	avg@64	pass@64	avg@4	pass@4	avg@8	pass@8	avg@4	pass@4	Avg.
DeepSeek-R1-1.5B	30.6	80.0	23.5	63.3	70.7	100.0	83.6	92.4	27.6	48.2	44.6	59.4	46.8
DAPO	42.1	80.0	28.6	56.7	80.3	97.5	87.6	94.6	29.2	46.3	53.2	65.8	53.5
DeepScaleR-1.5B	42.0	83.3	29.0	63.3	81.3	100.0	87.7	93.6	30.3	51.1	50.7	61.0	53.5
FastCuRL-1.5B-V3	48.1	80.0	32.7	60.0	86.4	95.0	89.8	94.0	33.6	50.0	55.3	64.3	57.7
Nemotron-1.5B	48.0	76.7	33.1	60.0	86.1	97.5	90.6	93.6	35.3	47.8	59.2	66.8	58.7
Archer-Math-1.5B	48.7	83.3	33.8	70.0	86.0	97.5	90.8	94.4	35.7	51.1	59.3	67.1	59.1

Method	LCB v5 (2024.08.01–2025.02.01)		LCB v6 (2025.02.01–2025.05.01)		Avg.
Method	avg@8	pass@8	avg@16	pass@16	Avg.
DeepSeek-R1-1.5B	16.7	29.0	17.2	34.4	17.0
DAPO	26.0	40.5	27.6	43.5	26.8
DeepCoder-1.5B	23.3	39.1	22.6	42.0	23.0
Nemotron-1.5B	26.1	35.5	29.5	42.8	27.8
Archer-Code-1.5B	29.4	43.7	30.2	45.8	29.8

Technical Report

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

Acknowledgements

We build our model upon DeepSeek-R1-Distill-Qwen-1.5B.
Training was carried out with a modified version of verl.

Citation

Please cite the following:

@article{wang2025stabilizing,
  title={Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR},
  author={Wang, Jiakang and Liu, Runze and Zhang, Fuzheng and Li, Xiu and Zhou, Guorui},
  journal={arXiv preprint arXiv:2507.15778},
  year={2025}
}