Qwen35-Agent-R2A103

<p align="center"> <img src="https://img.shields.io/badge/license-Apache--2.0-green"> <img src="https://img.shields.io/badge/Qwen3.5-35B%20A3B-blue"> <img src="https://img.shields.io/badge/MoE-256%20experts-orange"> <img src="https://img.shields.io/badge/Model_Soup-0.7%20R2%20%2B%200.3%20Agents--A1-ff69b4"> <img src="https://img.shields.io/badge/R2A103-purple"> </p> <p align="center"><b>🚀 Qwen35-Agent-R2A103 — R2 + Agents-A1 Model Soup (0.7 : 0.3)</b></p> <p align="center"><i>Building on hotdogs/Qwen35B-Agent-R2 as the base, blended with insights from InternScience/Agents-A1 via model soup (0.7 : 0.3).</i></p>

---

🧬 How This Model Was Built

┌──────────────────────────────────────────────────────────────────┐
│               Qwen35-Agent-R2A103 Construction                   │
├──────────────────────────────────────────────────────────────────┤
│                                                                  │
│  ┌─────────────────────┐      ┌──────────────────────────┐       │
│  │  Qwen35B-Agent-R2   │      │   InternScience/Agents-A1│       │
│  │  (7 LoRAs fused)    │      │   (Multi-teacher distilled)│      │
│  │  - Opus | Fable     │      │   - Tool Use | Reasoning  │       │
│  │  - Tool | Routing   │      │   - Search | Engineering  │       │
│  │  - Math | Mythos    │      │   - Scientific | Instruct │       │
│  │  - ToolFmt          │      │   - Full-domain SFT       │       │
│  └─────────┬───────────┘      └────────────┬──────────────┘       │
│            │                                │                      │
│            └────────── Model Soup ──────────┘                      │
│                        │  0.7 : 0.3                               │
│                        ▼                                          │
│            ┌──────────────────────┐                               │
│            │  Qwen35-Agent-R2A103 │                               │
│            │  31,666 tensors      │                               │
│            │  70.2 GB             │                               │
│            └──────────────────────┘                               │
│                        │                                          │
│                        ▼                                          │
│            ┌──────────────────────┐                               │
│            │  GGUF Quantization   │                               │
│            ├──────────────────────┤                               │
│            │ f16     → 65 GB      │                               │
│            │ Q4_K_M  → 20 GB      │                               │
│            │ Q6_K    → 27 GB      │                               │
│            └──────────────────────┘                               │
│                                                                  │
└──────────────────────────────────────────────────────────────────┘

Model Soup (Weight Averaging)

Building on hotdogs/Qwen35B-Agent-R2 as the base, we blend corresponding weight tensors with InternScience/Agents-A1:

W_R2A103 = 0.7 × W_R2 + 0.3 × W_Agents-A1

This preserves the agentic reasoning and tool-use capabilities of R2 while incorporating the broader multi-domain agent skills (long-horizon search, engineering, scientific research) from Agents-A1.

Architecture Compatibility

Both models share the same qwen3_5_moe architecture:

---

📦 Files

---

🚀 Usage

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "hotdogs/Qwen35-Agent-R2A103",
    device_map="auto",
    trust_remote_code=True,
    torch_dtype="auto",
)
tokenizer = AutoTokenizer.from_pretrained("hotdogs/Qwen35-Agent-R2A103")

messages = [{"role": "user", "content": "What is the capital of Thailand?"}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=256, temperature=0.6)
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))

With llama.cpp (GGUF)

# Q4_K_M (recommended - best size/speed/quality balance)
llama-cli \
  -m GGUF/Qwen35-Agent-R2A103.Q4_K_M.gguf \
  -n 256 -p "What is the capital of Thailand?" --temp 0.6 -ngl 99

# Or run as server:
llama-server \
  -m GGUF/Qwen35-Agent-R2A103.Q4_K_M.gguf \
  --port 8080 --host 0.0.0.0 -ngl 99 -c 4096

With Ollama

ollama create qwen35-r2a103 -f Modelfile
ollama run qwen35-r2a103

Modelfile:

FROM ./GGUF/Qwen35-Agent-R2A103.Q4_K_M.gguf

PARAMETER temperature 0.6
PARAMETER top_k 40
PARAMETER top_p 0.9
PARAMETER min_p 0.05
PARAMETER repeat_penalty 1.03

TEMPLATE "{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"

---

🧠 Capabilities

This model inherits skills from both parents:

---

📊 Performance

Benchmarked on 7× NVIDIA RTX 3090 with llama.cpp:

• Prompt processing: 41.7 t/s (11 tokens)
• Token generation: 92.1–110 t/s

---

🔗 References

• R2 Base: hotdogs/Qwen35B-Agent-R2
• Agents-A1: InternScience/Agents-A1
• Qwen3.5 MoE: Qwen/Qwen-AgentWorld-35B-A3B
• GGUF: llama.cpp

---

🙏 Credits

• hotdogs — Qwen35B-Agent-R2 as the base model
• InternScience / Agents-A1 — Multi-domain agent capabilities (tool-use, search, engineering, scientific reasoning, instruction following). Check out their paper
• Qwen Team (Alibaba) — Qwen3.5 MoE architecture
• llama.cpp — GGUF conversion and inference framework

---

📄 License

Apache 2.0