Instructions to use i-Coder/iCoder-27B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use i-Coder/iCoder-27B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="i-Coder/iCoder-27B-SFT")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("i-Coder/iCoder-27B-SFT")
model = AutoModelForMultimodalLM.from_pretrained("i-Coder/iCoder-27B-SFT", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use i-Coder/iCoder-27B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "i-Coder/iCoder-27B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "i-Coder/iCoder-27B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/i-Coder/iCoder-27B-SFT

SGLang

How to use i-Coder/iCoder-27B-SFT 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 "i-Coder/iCoder-27B-SFT" \
    --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": "i-Coder/iCoder-27B-SFT",
		"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 "i-Coder/iCoder-27B-SFT" \
        --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": "i-Coder/iCoder-27B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use i-Coder/iCoder-27B-SFT with Docker Model Runner:
```
docker model run hf.co/i-Coder/iCoder-27B-SFT
```

iCoder-27B-SFT / README.md

greeky

iCoder-27B-SFT

eab7909 2 days ago

preview code

Raw

History Blame Contribute Delete

2.09 kB

metadata

license: apache-2.0
base_model:
  - Qwen/Qwen3.6-27B
base_model_relation: finetune
pipeline_tag: text-generation
library_name: transformers
tags:
  - code
  - rtl
  - verilog
  - gpu-kernel
  - triton

iCoder-27B-SFT

An intermediate checkpoint from the iCoder-27B training pipeline. The released model is i-Coder/iCoder-27B.

Qwen3.6-27B  ──▶  [ SFT ]  ──▶  OPSD  ──▶  RLVR  ──▶  iCoder-27B
                    ▲
                    this checkpoint

Model description

iCoder-27B is a 27B model for RTL design and GPU kernel optimization, developed by an agent that runs and revises each stage of its own training pipeline.

This checkpoint is the output of the first stage, supervised fine-tuning on verified teacher trajectories. It starts from Qwen3.6-27B. Two stages follow: OPSD, which yields iCoder-27B-OPSD, and RLVR, which produces the released model.

The method and the reported results are described in the technical report.

Intended use

Research on the training pipeline: reproducing this stage, ablating it, or measuring what the later stages add on top of it. This is a mid-pipeline artifact and has had no deployment preparation.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "i-Coder/iCoder-27B-SFT"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, dtype="auto", device_map="auto"
)

messages = [{"role": "user", "content": "Write a 4-bit synchronous up counter with active-low reset in Verilog."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=2048)
print(tokenizer.decode(out[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

License

Apache-2.0, inherited from the base model, Qwen3.6-27B.