Instructions to use meissosisai/Arc1-Coder-14b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meissosisai/Arc1-Coder-14b with Transformers:

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

pipe = pipeline("text-generation", model="meissosisai/Arc1-Coder-14b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meissosisai/Arc1-Coder-14b")
model = AutoModelForCausalLM.from_pretrained("meissosisai/Arc1-Coder-14b")
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 Settings

vLLM

How to use meissosisai/Arc1-Coder-14b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meissosisai/Arc1-Coder-14b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meissosisai/Arc1-Coder-14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meissosisai/Arc1-Coder-14b

SGLang

How to use meissosisai/Arc1-Coder-14b 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 "meissosisai/Arc1-Coder-14b" \
    --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": "meissosisai/Arc1-Coder-14b",
		"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 "meissosisai/Arc1-Coder-14b" \
        --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": "meissosisai/Arc1-Coder-14b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meissosisai/Arc1-Coder-14b with Docker Model Runner:
```
docker model run hf.co/meissosisai/Arc1-Coder-14b
```

Model Card: Arc1-Coder-14b

1. Model Overview

Arc1-Coder-14b is a state-of-the-art (SOTA) large language model purpose-built for advanced programming tasks and algorithmic reasoning. Developed by Meissosis AI INC., it leverages the robust Qwen2.5-Coder architecture as a foundation, enhanced by a proprietary reinforcement learning pipeline designed to minimize logical hallucinations and maximize code correctness.

Developer: Meissosis AI INC.
Model Type: Causal Language Model
Parameters: 14.7 Billion
Language(s): Multilingual (92+ programming languages)
License: Apache 2.0

2. Technical Specifications

Attribute	Specification
Architecture	Transformer-based Decoder-Only (Qwen2.5)
Layers	48
Attention Mechanism	Grouped-Query Attention (GQA)
Context Length	128,000 tokens
Training Precision	bfloat16
Vocabulary Size	151,936

3. Training Methodology

Arc1-Coder-14b was refined using a two-stage post-training process:

Curated SFT: Fine-tuned on a high-density dataset of verified competitive programming solutions and complex system design documents.
Outcome-Based RL (OBRL): Trained using a reward model that validates code execution results rather than just text similarity, significantly improving the "Pass@1" success rate on zero-shot tasks.

4. Benchmark Performance (2026 Standards)

Results based on greedy decoding (temperature=0).

Benchmark	Score (Pass@1)	Comparison (Industry Avg 14B)
HumanEval	88.4%	81.2%
MBPP	87.2%	82.5%
LiveCodeBench	64.2%	55.8%

5. Usage & Implementation

Inference Requirements

VRAM: ~30GB for bfloat16 inference; ~12GB for 4-bit quantized inference.
Recommended Precision: dtype=torch.bfloat16

Example Loading (Transformers v4.40+)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "zhlajiex/Arc1-Coder-14b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

Downloads last month: 5

Safetensors

Model size

15B params

Tensor type

F32

F16