Upload 2 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+All_charts.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,319 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+language:
+- en
+- es
+- fr
+- de
+- it
+- pt
+- ru
+- ar
+- hi
+- ko
+- zh
+library_name: transformers
+base_model:
+- arcee-ai/Trinity-Large-Base
+arxiv:
+- 2602.17004
+tags:
+- reasoning
+- agentic
+- tool-calling
+- thinking
+---
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable html -->
+<!-- markdownlint-disable no-duplicate-header -->
+
+```
+Missing MXFP4_MOE GGUF quantization of Arcee AI Trinity Large Thinging model
+with full output tensors precission
+
+llama.cpp version: 8701 (66c4f9ded)
+```
+
+<div align="center">
+  <picture>
+    <img
+      src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/i-v1KyAMOW_mgVGeic9WJ.png"
+      alt="Arcee Trinity Large Thinking"
+      style="max-width: 100%; height: auto;"
+    >
+  </picture>
+</div>
+<hr>
+
+# Trinity-Large-Thinking
+
+## Introduction
+
+Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token. Built on Trinity-Large-Base and post-trained with extended chain-of-thought reasoning and agentic RL, Trinity-Large-Thinking delivers state-of-the-art performance on agentic benchmarks while maintaining strong general capabilities.
+
+Trinity-Large-Thinking generates explicit reasoning traces wrapped in `<think>...</think>` blocks before producing its final response. This thinking process is critical to the model's performance — **thinking tokens must be kept in context** for multi-turn conversations and agentic loops to function correctly.
+
+Try it at [chat.arcee.ai](http://chat.arcee.ai/)
+
+More details on the training of Trinity Large are available in the [technical report](https://arxiv.org/abs/2602.17004).
+
+## Key Highlights
+
+- **Agentic-first design**: Purpose-built for tool calling, multi-step planning, and agent workflows
+- **State-of-the-art agentic performance**: 94.7% on τ²-Bench, 91.9% on PinchBench, 98.2% on LiveCodeBench
+- **Native reasoning traces**: Extended chain-of-thought via `<think>...</think>` blocks
+- **Compatible with major agent frameworks**: Works out of the box with [OpenClaw](https://github.com/openclaw) and [Hermes Agent](https://github.com/NousResearch/hermes-agent)
+- **Ready to use on [OpenRouter](https://openrouter.ai/)**: No setup required — full reasoning and tool calling support via API
+
+## Model Variants
+
+The Trinity Large family consists of four checkpoints:
+
+- **Trinity-Large-Thinking** (this release): Reasoning-optimized, agentic post-training with extended chain-of-thought
+- **[Trinity-Large-Preview](https://huggingface.co/arcee-ai/Trinity-Large-Preview)**: Lightly post-trained, chat-ready instruct model (no reasoning_content).
+- **[Trinity-Large-TrueBase](https://huggingface.co/arcee-ai/Trinity-Large-TrueBase)**: 10T-token pre-anneal pretraining checkpoint
+- **[Trinity-Large-Base](https://huggingface.co/arcee-ai/Trinity-Large-Base)**: Full 17T-token pretrained foundation model with mid-training anneals
+
+## Architecture
+
+Trinity-Large-Thinking shares the same sparse MoE architecture as Trinity-Large-Preview.
+
+| Hyperparameter | Value |
+|:---|:---:|
+| Total parameters | ~398B |
+| Active parameters per token | ~13B |
+| Experts | 256 (1 shared) |
+| Active experts | 4 |
+| Routing strategy | 4-of-256 (1.56% sparsity) |
+| Dense layers | 6 |
+| Pretraining context length | 8,192 |
+| Context length after extension | 512k |
+| Architecture | Sparse MoE (AfmoeForCausalLM) |
+
+## Benchmarks
+![Benchmark charts](https://huggingface.co/arcee-ai/Trinity-Large-Thinking/resolve/main/All_charts.jpg)
+
+| Benchmark | Trinity-Large-Thinking | Opus-4.6 | GLM-5 | MiniMax-M2.7 | Kimi-K2.5 |
+|---|---:|---:|---:|---:|---:|
+| IFBench | 52.3 | 53.1 | 72.3 | **75.7** | 70.2 |
+| GPQA-Diamond | 76.3 | **89.2** | 81.6 | 86.2 | 86.9 |
+| Tau2-Airline | **88.0** | 82.0 | 80.5 | 80.0 | 80.0 |
+| Tau2-Telecom | 94.7 | 92.1 | **98.2** | 84.8 | 95.9 |
+| PinchBench | 91.9 | **93.3** | 86.4 | 89.8 | 84.8 |
+| AIME25 | 96.3 | **99.8** | 93.3 | 80.0 | 96.3 |
+| BCFLv4 | 70.1 | **77.0** | 70.8 | 70.6 | 68.3 |
+| MMLU-Pro | 83.4 | **89.1** | 85.8 | 80.8 | 87.1 |
+| SWE-bench Verified* | 63.2 | **75.6** | 72.8 | 75.4 | 70.8 |
+
+ *All models evaluated in mini-swe-agent-v2
+
+## Thinking-in-Context: Important Usage Note
+
+Trinity-Large-Thinking produces reasoning traces inside `<think>...</think>` blocks before generating its final response.
+
+This means:
+
+1. **Multi-turn conversations**: When building chat applications, include the full assistant response (thinking + answer) in the conversation history for subsequent turns.
+2. **Agentic loops**: When using Trinity-Large-Thinking as the backbone of an agent (OpenClaw, Hermes Agent, or custom), ensure your tool-calling loop preserves `<think>` blocks in the message history between steps.
+3. **Context window management**: The 512k extended context window accommodates long reasoning chains across many agentic steps. If you must truncate history, prefer removing older turns entirely rather than stripping thinking tokens from recent turns.
+
+### How thinking works
+
+The model reasons internally before producing its response. When served via vLLM, the reasoning is separated into a dedicated `reasoning_content` field in the API response:
+
+    // API response structure
+    {
+      "message": {
+        "role": "assistant",
+        "reasoning_content": "The user wants flight information. I need to determine the date for next Tuesday, search for flights SFO → JFK, and filter by price < $300.",
+        "content": "\n",
+        "tool_calls": [{
+          "function": {
+            "name": "search_flights",
+            "arguments": "{\"origin\": \"SFO\", \"destination\": \"JFK\", \"date\": \"2026-04-07\", \"max_price\": 300}"
+          }
+        }]
+      }
+    }
+
+When building multi-turn agentic loops, include the `reasoning_content` back in the conversation history (re-wrapped in `<think>...</think>` tags within the assistant message) so the model retains its prior reasoning chain.
+
+## Training Configuration
+
+### Pretraining
+
+- Training tokens: 17 trillion
+- Data partner: [Datology](https://www.datologyai.com/)
+
+### Posttraining
+
+- Instruction tuning and agentic RL with extended chain-of-thought
+- Trained on tool-calling trajectories, multi-step agent tasks, and reasoning chains
+
+### Infrastructure
+
+- Hardware: 2,048 NVIDIA B300 GPUs
+- Parallelism: HSDP + Expert Parallelism
+- Compute partner: [Prime Intellect](https://www.primeintellect.ai/)
+
+## Usage
+
+### Running our model
+
+- [vLLM](#vllm) (recommended for agentic deployments)
+- [Transformers](#transformers)
+- [API](#api)
+
+### vLLM
+
+Supported in vLLM 0.11.1+. For agentic use with both reasoning and tool calling:
+
+    vllm serve arcee-ai/Trinity-Large-Thinking \
+      --dtype bfloat16 \
+      --enable-reasoning \
+      --reasoning-parser deepseek_r1 \
+      --enable-auto-tool-choice \
+      --tool-call-parser qwen3_coder
+
+This configuration:
+- `--reasoning-parser deepseek_r1` — Parses `<think>...</think>` reasoning blocks and exposes them via the `reasoning_content` field in the API response
+- `--tool-call-parser qwen3_coder` — Parses structured tool calls from the model output into the OpenAI-compatible `tool_calls` array
+
+**Extracting reasoning content from the API response:**
+
+```python
+from openai import OpenAI
+
+client = OpenAI(api_key="EMPTY", base_url="http://localhost:8000/v1")
+
+response = client.chat.completions.create(
+    model="arcee-ai/Trinity-Large-Thinking",
+    messages=[
+        {"role": "user", "content": "What's the weather like in Paris?"}
+    ],
+    tools=[ # your tool definitions here
+        {
+            "type": "function",
+            "function": {
+                "name": "get_weather",
+                "description": "Get current weather for a location",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {"type": "string"}
+                    },
+                    "required": ["location"]
+                }
+            }
+        }
+    ],
+)
+
+# Access reasoning (thinking) content
+reasoning = response.choices[0].message.reasoning_content
+
+# Access final response or tool calls
+content = response.choices[0].message.content
+tool_calls = response.choices[0].message.tool_calls
+```
+
+**Note on thinking-in-context with vLLM**: When building multi-turn agentic loops, include both `reasoning_content` and `content` in the conversation history you send back to the model. The reasoning content should be re-wrapped in `<think>...</think>` tags within the assistant message.
+
+### Transformers
+
+Use the `main` transformers branch or pass `trust_remote_code=True` with a released version.
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "arcee-ai/Trinity-Large-Thinking"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True
+)
+
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=4096,
+    do_sample=True,
+    temperature=0.6,
+    top_k=50,
+    top_p=0.95
+)
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+
+### API
+
+Available on OpenRouter:
+
+    curl -X POST "https://openrouter.ai/v1/chat/completions" \
+      -H "Authorization: Bearer $OPENROUTER_API_KEY" \
+      -H "Content-Type: application/json" \
+      -d '{
+        "model": "arcee-ai/trinity-large-thinking",
+        "messages": [
+          {
+            "role": "user",
+            "content": "What are some fun things to do in New York?"
+          }
+        ]
+      }'
+
+## Agentic Use Cases
+
+Trinity-Large-Thinking is optimized for deployment as the reasoning backbone of AI agent systems. It has been evaluated and performs excellently with:
+
+### OpenClaw
+
+Trinity-Large-Thinking works as a drop-in brain for OpenClaw agents. Its native tool-calling format is compatible with OpenClaw's execution loop, and the extended reasoning enables reliable multi-step task completion — from email triage to code generation to meeting scheduling. Our 91.9% PinchBench score reflects real-world OpenClaw task performance.
+
+### Hermes Agent
+
+Compatible with the Hermes Agent framework from Nous Research. Trinity-Large-Thinking's reasoning traces pair naturally with Hermes's skill-learning loop — the model's explicit chain-of-thought makes skill extraction more reliable, and its strong tool-calling capabilities integrate directly via the Hermes tool-use protocol.
+
+### Custom Agent Loops
+
+For custom implementations, the key integration pattern is:
+
+1. Send the user message with tool definitions
+2. Receive the response with `<think>` reasoning + tool calls
+3. Execute the tool calls
+4. Append the **full** assistant response (thinking + content + tool calls) and tool results to the message history
+5. Send the updated history back for the next step
+6. Repeat until the model produces a final response without tool calls
+
+## License
+
+Trinity-Large-Thinking is released under the Apache License, Version 2.0.
+
+## Citation
+
+If you use this model, please cite:
+
+    @misc{singh2026arceetrinity,
+      title        = {Arcee Trinity Large Technical Report},
+      author       = {Varun Singh and Lucas Krauss and Sami Jaghouar and Matej Sirovatka and Charles Goddard and Fares Obied and Jack Min Ong and Jannik Straube and Fern and Aria Harley and Conner Stewart and Colin Kealty and Maziyar Panahi and Simon Kirsten and Anushka Deshpande and Anneketh Vij and Arthur Bresnu and Pranav Veldurthi and Raghav Ravishankar and Hardik Bishnoi and DatologyAI Team and Arcee AI Team and Prime Intellect Team and Mark McQuade and Johannes Hagemann and Lucas Atkins},
+      year         = {2026},
+      eprint       = {2602.17004},
+      archivePrefix= {arXiv},
+      primaryClass = {cs.LG},
+      doi          = {10.48550/arXiv.2602.17004},
+      url          = {https://arxiv.org/abs/2602.17004}
+    }