Ornith-1.0: self-improving open-source models for agentic coding

Uh oh!

There was an error while loading. Please reload this page.

Notifications You must be signed in to change notification settings

Fork 37

Star 350

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

10 Commits

10 Commits

assets

assets

.gitignore

.gitignore

LICENSE

LICENSE

README.md

README.md

Repository files navigation

Ornith-1.0

Aloha! 🌺 Ornith-1.0 is a self-improving open-source models for agentic coding.

Highlights:

State-of-the-Art Coding Agents: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.

Self-Improving Training Framework: Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model discovers better search trajectories and generates higher-quality solutions.

Licence: MIT licensed, globally accessible, and free from regional limitations.

Benchmarks

Each model is evaluated against its size-appropriate baselines. All three use the same harnesses and decoding setup (see the notes under the tables).

Ornith-1.0-9B

Ornith-1.0-9B Qwen3.5-9B Qwen3.5-35B Gemma4-12B Gemma4-31B

Agentic Coding

Terminal-Bench 2.1 (Terminus-2)43.121.341.42142.1

Terminal-Bench 2.1 (Claude Code)40.618.938.9--

SWE-bench Verified69.453.27044.252

SWE-bench Pro42.931.344.627.635.7

SWE-bench Multilingual5239.760.332.551.7

NL2Repo27.216.220.510.315.5

Claw-eval Avg63.153.265.432.548.5

SWE Atlas - QnA17.99.213.2--

SWE Atlas - RF16.64.310.2--

SWE Atlas - TW15.34.49.8--

Ornith-1.0-35B

Ornith-1.0-35B Qwen3.5-35B Qwen3.6-35B Gemma4-31B Qwen3.5-397B

Agentic Coding

Terminal-Bench 2.1 (Terminus-2)64.241.452.542.153.5

Terminal-Bench 2.1 (Claude Code)62.838.949.2-48.6

SWE-bench Verified75.67073.45276.4

SWE-bench Pro50.444.649.535.751.6

SWE-bench Multilingual69.360.367.251.769.3

NL2Repo34.620.529.415.536.8

Claw-eval Avg69.865.468.748.570.7

SWE Atlas - QnA37.113.215.5-20.4

SWE Atlas - RF29.710.211.4-18.4

SWE Atlas - TW27.89.813.3-18.5

Ornith-1.0-397B

Ornith-1.0-397B Qwen3.5-397B Qwen3.7-Max GLM-5.2-744B Minimax-M3-428B DeepSeek-V4-Pro-1.6T Claude Opus 4.7 Claude Opus 4.8

Agentic Coding

Terminal-Bench 2.1 (Terminus-2)77.553.573.581.0646470.385

Terminal-Bench 2.1 (Claude Code)78.248.669.882.7-66.569.778.9

SWE-bench Verified82.476.480.4--80.680.887.6

SWE-bench Pro62.251.660.662.15955.464.369.2

SWE-bench Multilingual78.969.378.3--76.2--

NL2Repo48.236.847.248.942.1--69.7

Claw-eval Avg77.170.765.2--75.878.2-

SWE Atlas - QnA41.220.4--37.927.240.348.8

SWE Atlas - RF42.618.4----48.646.7

SWE Atlas - TW39.118.5--30.8-38.5-

• Terminal-Bench 2.1 (Terminus-2): evaluated with the Harbor/Terminus-2 framework, parser=json, temperature=1.0, top_p=1.0, 128K context window. Each run uses a 4-hour timeout with 32 CPU cores and 48GB RAM, averaged over 5 runs. We adjust the Qwen chat template to keep training and inference consistent and modify Harbor to align with vLLM's reasoning_content key.

• Terminal-Bench 2.1 (Claude Code): evaluated with Claude Code 2.1.126, parser=json, temperature=1.0, top_p=1.0, max_new_tokens=131072, averaged over 5 runs (Qwen chat template likewise modified).

• SWE-bench Verified / Pro / Multilingual: OpenHands harness, temp=1.0, top_p=0.95, 256K context window.

• SWE Atlas QnA / RF / TW: mini-SWE-agent harness, temp=1.0, top_p=0.95, 128K context window, averaged over 5 runs.

• NL2Repo: temperature=1.0, top_p=1.0, 400K context, 48K output, anti-hacking filters.

• ClawEval: an agentic code benchmark over real-user task distributions; temp=0.6, 256K context.

Quickstart

NOTE

Ornith-1.0 is a reasoning model: by default the assistant turn opens with a … block before the final answer. The serving recipes below enable a reasoning parser so the chain-of-thought is returned in a separate reasoning_content field, and a tool-call parser so the model's blocks are surfaced as OpenAI-style tool_calls.

Serving Ornith-1.0 requires recent runtimes:

Transformers ≥ 5.8.1

vLLM ≥ 0.19.1

SGLang ≥ 0.5.9

Recommended sampling parameters: temperature=0.6, top_p=0.95, top_k=20 (use temperature=1.0 to reproduce the reported benchmark setup).

Serving Ornith-1.0

Ornith-1.0 ships as a dense 9B model plus two Mixture-of-Experts models (35B, 397B). All checkpoints expose the same OpenAI-compatible interface and support a 256K (262,144-token) context window; the dense 9B fits on a single 80GB GPU, while the MoE checkpoints are sharded across a multi-GPU node with tensor parallelism. Each size is published in multiple precision / format variants:

Checkpoint Architecture Format Best for

Ornith-1.0-9B Dense (~9B) bf16 Single-GPU serving & fine-tuning

Ornith-1.0-9B-GGUF Dense (~9B) GGUF (quantized) Local inference via llama.cpp / Ollama

Ornith-1.0-35B MoE (35B) bf16 Full-precision multi-GPU serving

Ornith-1.0-35B-FP8 MoE (35B) FP8 ~Half the VRAM on FP8-capable GPUs

Ornith-1.0-35B-GGUF MoE (35B) GGUF (quantized) Local inference via llama.cpp / Ollama

Ornith-1.0-397B MoE (397B) bf16 Full-precision serving on a multi-GPU node

Ornith-1.0-397B-FP8 MoE (397B) FP8 Memory-efficient serving on FP8-capable GPUs

The recipes below stand up an OpenAI-compatible server under the shared alias Ornith-1.0. Set MODEL to the checkpoint you want, and match --tensor-parallel-size / --tp to your GPU count.

vLLM

Pick a checkpoint — dense 9B, or MoE 35B / 397B (append -FP8 for lower-VRAM serving):

MODEL=deepreinforce-ai/Ornith-1.0-397B

MoE checkpoints (35B / 397B): shard across the node with tensor parallelism.

Dense checkpoint (9B): fits on a single 80GB GPU — drop --tensor-parallel-size.

vllm serve $MODEL \ --served-model-name Ornith-1.0 \ --tensor-parallel-size 8 \ --host 0.0.0.0 --port 8000 \ --max-model-len 262144 \ --gpu-memory-utilization 0.90 \ --enable-prefix-caching \ --enable-auto-tool-choice --tool-call-parser qwen3_xml \ --reasoning-parser qwen3 \ --trust-remote-code

SGLang

Pick a checkpoint — dense 9B, or MoE 35B / 397B (append -FP8 for lower-VRAM serving):

MODEL=deepreinforce-ai/Ornith-1.0-397B

MoE checkpoints (35B / 397B): shard with --tp ; dense 9B: drop --tp for a single GPU.

python -m sglang.launch_server \ --model-path $MODEL \ --served-model-name Ornith-1.0 \ --tp 8 \ --host 0.0.0.0 --port 8000 \ --context-length 262144 \ --mem-fraction-static 0.85 \ --tool-call-parser qwen3_coder \ --reasoning-parser qwen3

Hugging Face Transformers

For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0 requires transformers >= 5.8.1. The dense 9B checkpoint is the easiest to run locally.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "deepreinforce-ai/Ornith-1.0-9B" # or -35B / -397B

tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, dtype="auto", device_map="auto", )

messages = [ {"role": "user", "content": "Write a Python function is_prime(n). Keep it short."} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, )

inputs = tokenizer(text, return_tensors="pt").to(model.device) generated = model.generate( **inputs, max_new_tokens=512, do_sample=True, temperature=0.6, top_p=0.95, top_k=20, ) output_ids = generated[0][inputs.input_ids.shape[1]:]

The reply contains a ... reasoning block followed by the answer.

content = tokenizer.decode(output_ids, skip_special_tokens=True) print(content)

To split the reasoning trace from the final answer, parse on the marker:

text = tokenizer.decode(output_ids, skip_special_tokens=True) if "" in text: reasoning, answer = text.split("", 1) reasoning = reasoning.replace("", "").strip() answer = answer.strip() else: reasoning, answer = "", text.strip()

Using Ornith-1.0 via the Chat Completions API

Once a vLLM or SGLang server is running, talk to it with any OpenAI-compatible client.

Basic Usage

from openai import OpenAI

client = OpenAI( base_url="http://localhost:8000/v1", api_key="EMPTY", # any non-empty string works for a local server )

response = client.chat.completions.create( model="Ornith-1.0", messages=[ {"role": "user", "content": "Write a one-line Python lambda that squares a number."} ], temperature=0.6, top_p=0.95, max_tokens=1024, )

message = response.choices[0].message

reasoning_content holds the trace; content holds the final answer.

print("reasoning:", getattr(message, "reasoning_content", None)) print("answer:", message.content)

You can also stream tokens, or hand the model tools — Ornith-1.0 emits well-formed function calls that the server parses into the standard tool_calls field:

tools = [ { "type": "function", "function": { "name": "get_weather", "description": "Get the current weather for a city", "parameters": { "type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"], }, }, } ]

response = client.chat.completions.create( model="Ornith-1.0", messages=[{"role": "user", "content": "What is the weather in Paris right now?"}], tools=tools, tool_choice="auto", temperature=0.6, max_tokens=2048, )

tool_call = response.choices[0].message.tool_calls[0] print(tool_call.function.name, tool_call.function.arguments)

-> get_weather {"city": "Paris"}

You can point any OpenAI-compatible SDK (Python, Node.js, etc.) or curl at the same /v1/chat/completions endpoint.

Agentic Usage

Ornith-1.0 excels in tool-calling and agentic coding capabilities.

Agent Frameworks

Because Ornith-1.0 exposes an OpenAI-compatible endpoint with tool calling, it works out of the box with standard agent frameworks. Below is a minimal example that connects Ornith-1.0 to tools through an MCP server.

import os from openai import OpenAI

client = OpenAI( base_url=os.getenv("OPENAI_BASE_URL", "http://localhost:8000/v1"), api_key=os.getenv("OPENAI_API_KEY", "EMPTY"), )

tools = [ { "type": "function", "function": { "name": "run_shell", "description": "Run a shell command and return its output.", "parameters": { "type": "object", "properties": { "command": {"type": "string", "description": "The command to run"} }, "required": ["command"], }, }, } ]

messages = [{"role": "user", "content": "List the Python files in the current directory."}]

response = client.chat.completions.create( model="Ornith-1.0", messages=messages, tools=tools, temperature=0.6, top_p=0.95, ) print(response.choices[0].message)

Examples of using Ornith with agent harness:

Hermes Agent

Hermes talks to any OpenAI-compatible endpoint — point it at your Ornith server.

export OPENAI_BASE_URL="http://localhost:8000/v1" export OPENAI_API_KEY="EMPTY" export MODEL="Ornith-1.0"

OpenHands

pip install openhands-ai

OpenHands routes through LiteLLM; the "openai/" prefix selects the OpenAI-compatible path.

export LLM_MODEL="openai/Ornith-1.0" export LLM_BASE_URL="http://localhost:8000/v1" export LLM_API_KEY="EMPTY"

Launch the CLI (or run the official OpenHands Docker image with the same env vars).

openhands

llama.cpp / Ollama

Both runtimes load a GGUF build — available for the 9B and 35B checkpoints (swap -9B for -35B).

llama.cpp — serve an OpenAI-compatible API on port 8000.

llama-server -hf deepreinforce-ai/Ornith-1.0-9B-GGUF --port 8000 -c 262144

Ollama — pull and chat with the same GGUF straight from Hugging Face.

ollama run hf.co/deepreinforce-ai/Ornith-1.0-9B-GGUF

Unsloth Studio

pip install unsloth

Load Ornith for fast local inference or fine-tuning (Python):

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(

"d

[truncated for AI cost control]