---
title: Orbit
canonical_url: "https://www.modelscope.cn/models/beyoru-ai/Orbit"
md_url: "https://www.modelscope.cn/models/beyoru-ai/Orbit.md"
repository: beyoru-ai/Orbit
last_updated: 2026-08-11
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
base_model:
  - Qwen/Qwen3.5-35B-A3B
base_model_relation: finetune
parameters: 35.1B
tensor_type:
  - BF16
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - vi
  - en
downloads: 22
stars: 0
tags:
  - agent
  - tool-use
  - reasoning
  - esft
  - claude-opus-5
  - xhigh
  - distillation
  - coding
  - terminal
  - moe
---

# Orbit

> Orbit - beyoru-ai 在 ModelScope 开源的模型。Expert-Specialized Fine-Tune (ESFT) of Qwen/Qwen3.5-35B-A3B for Vietnamese multi-turn tool-use, trained on reasoning traces.

beyoru-ai/Orbit 是 ModelScope 魔搭社区上的 35.1B 参数text-generation模型，采用 mit 许可，基于 Qwen/Qwen3.5-35B-A3B 构建。

- **Repository**: beyoru-ai/Orbit
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 35.1B
- **Base model**: Qwen/Qwen3.5-35B-A3B
- **Tags**: agent, tool-use, reasoning, esft, claude-opus-5, xhigh, distillation, coding, terminal, moe
- **Downloads**: 22
- **Stars**: 0
- **Last updated**: 2026-08-11

Source: https://www.modelscope.cn/models/beyoru-ai/Orbit

---

# Orbit

Expert-Specialized Fine-Tune (ESFT) of
[`Qwen/Qwen3.5-35B-A3B`](https://huggingface.co/Qwen/Qwen3.5-35B-A3B)
for Vietnamese multi-turn tool-use, trained on reasoning traces.

Architecture is unchanged from the base model.

This model was training on the distillation dataset from `claude-opus-5`, effort `xhigh` for my custome workflow

# Capabilities
## Multi-turn tool use
This model is trained to maintain context across multiple tool interactions,
rather than treating each tool call as an isolated operation.
This makes it suitable for workflows where the result of one action determines
the next action.

## Tool selection

The model is trained on trajectories containing tool selection and execution,
allowing it to reason about:

- which tool should be used
- when a tool call is necessary
- what arguments should be provided
- how to interpret tool results
- whether additional actions are required

The training data contains high-effort reasoning trajectorie

## Training

- **ESFT**: only selected MoE experts are trained (router frozen).
- trainable: ~0.94B of 35.6B parameters (2.6%)
- expert selection: `top_p = 0.20`, ~7.5 of 256 experts per layer
- single NVIDIA GB10 (121 GB unified memory)

## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tk = AutoTokenizer.from_pretrained("beyoru/Clawd-Agent")
model = AutoModelForCausalLM.from_pretrained("beyoru/Clawd-Agent", dtype="auto", device_map="auto")

msgs = [{"role": "user", "content": "..."}]
ids = tk.apply_chat_template(msgs, tools=TOOLS, add_generation_prompt=True, return_tensors="pt")
```

Serving with vLLM:

```bash
vllm serve beyoru/Orbit --max-model-len 8192
```

The chat template emits `<think>\n` in the generation prompt, so the model continues the
reasoning block and closes it with `</think>` before the answer.

## Note

Inherits the base model's MIT license. Fine-tuned on a narrow task distribution — evaluate on
your own workload before relying on it for anything outside multi-turn tool use.