add python codes to code blocks

.eval_results/gpqa.yaml

@@ -1,7 +0,0 @@
-- dataset:
-    id: Idavidrein/gpqa
-    task_id: diamond
-  value: 76.3
-  source:
-    url: https://huggingface.co/arcee-ai/Trinity-Large-Thinking
-    name: Model Card

.eval_results/mmlu-pro.yaml

@@ -1,7 +0,0 @@
-- dataset:
-    id: TIGER-Lab/MMLU-Pro
-    task_id: mmlu_pro
-  value: 83.4
-  source:
-    url: https://huggingface.co/arcee-ai/Trinity-Large-Thinking
-    name: Model Card

.eval_results/swe-bench_verified.yaml

@@ -1,7 +0,0 @@
-- dataset:
-    id: SWE-bench/SWE-bench_Verified
-    task_id: swe_bench_%_resolved
-  value: 63.2
-  source:
-    url: https://huggingface.co/arcee-ai/Trinity-Large-Thinking
-    name: Model Card

.gitattributes

@@ -34,5 +34,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
-All[[:space:]]charts.jpg filter=lfs diff=lfs merge=lfs -text
-All_charts.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -84,7 +84,6 @@ Trinity-Large-Thinking shares the same sparse MoE architecture as Trinity-Large-
 | 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 |
 |---|---:|---:|---:|---:|---:|
@@ -107,37 +106,29 @@ Trinity-Large-Thinking produces reasoning traces inside `<think>...</think>` blo
 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 reasoning in the message history between steps.
+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 field in the API response:
-
-```json
-// API response structure
-{
-  "message": {
-    "role": "assistant",
-    "reasoning": "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}"
+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}"
+          }
+        }]
       }
-    }]
-  }
-}
-```
-
-### Preserving reasoning in multi-turn conversations
-
-When building multi-turn agentic loops, you **must** pass the reasoning field back on assistant messages in subsequent requests. The chat template reads this field and re-wraps it in `<think>...</think>` tags during tokenization, maintaining the model's chain-of-thought across turns.
+    }
 
-**⚠️ Field name compatibility**: In vLLM OpenAI-compatible chat APIs, input compatibility for `reasoning_content` can vary by version, and some versions only honor `reasoning` ([related issue](https://github.com/vllm-project/vllm/issues/38488)). For maximum compatibility in multi-turn loops, send assistant reasoning back as `reasoning`. If your SDK exposes `reasoning_content` in responses, map it to `reasoning` when appending assistant turns.
-
-**What happens if reasoning is omitted entirely?** If the assistant message has no reasoning field at all (neither `reasoning` nor `reasoning_content`), or if `content` is `null`, the model can lose prior chain-of-thought context. On simple tasks this may work fine, but on complex multi-step agentic tasks, the model can produce malformed tool calls (e.g., tool call XML appearing inside the reasoning field instead of as structured `tool_calls`). For best results, always preserve the reasoning field and use `""` instead of `null` for content on tool-call turns.
+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
 
@@ -169,20 +160,18 @@ When building multi-turn agentic loops, you **must** pass the reasoning field ba
 
 Supported in vLLM 0.11.1+. For agentic use with both reasoning and tool calling:
 
-```bash
-vllm serve arcee-ai/Trinity-Large-Thinking \
-  --dtype bfloat16 \
-  --reasoning-parser deepseek_r1 \
-  --enable-auto-tool-choice \
-  --tool-call-parser qwen3_coder
-```
+    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` field in the API response
+- `--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
 
-
-#### Single-turn example
+**Extracting reasoning content from the API response:**
 
 ```python
 from openai import OpenAI
@@ -194,18 +183,22 @@ response = client.chat.completions.create(
     messages=[
         {"role": "user", "content": "What's the weather like in Paris?"}
     ],
-    tools=[{
-        "type": "function",
-        "function": {
-            "name": "get_weather",
-            "description": "Get current weather for a location",
-            "parameters": {
-                "type": "object",
-                "properties": {"location": {"type": "string"}},
-                "required": ["location"]
+    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
@@ -216,87 +209,7 @@ content = response.choices[0].message.content
 tool_calls = response.choices[0].message.tool_calls
 ```
 
-#### Multi-turn agentic loop example
-
-The key pattern: after each turn, append the **full** assistant response (including reasoning) back to the message history, then append tool results, and send the updated history for the next turn.
-
-```python
-import json
-from openai import OpenAI
-
-client = OpenAI(api_key="EMPTY", base_url="http://localhost:8000/v1")
-MODEL = "arcee-ai/Trinity-Large-Thinking"
-
-tools = [
-    {"type": "function", "function": {
-        "name": "get_customer_by_email",
-        "description": "Look up a customer by email.",
-        "parameters": {"type": "object", "properties": {"email": {"type": "string"}}, "required": ["email"]}
-    }},
-    {"type": "function", "function": {
-        "name": "cancel_subscription",
-        "description": "Cancel a subscription. Requires customer_id.",
-        "parameters": {"type": "object", "properties": {"customer_id": {"type": "string"}, "reason": {"type": "string"}}, "required": ["customer_id"]}
-    }}
-]
-
-def execute_tool(name, arguments):
-    """Simulate tool execution — replace with real implementations."""
-    args = json.loads(arguments)
-    if name == "get_customer_by_email":
-        return json.dumps({"customer_id": "C2001", "name": "Jane Doe", "plan": "Premium", "status": "active"})
-    elif name == "cancel_subscription":
-        return json.dumps({"success": True, "message": f"Subscription cancelled for {args['customer_id']}"})
-
-messages = [
-    {"role": "system", "content": "You are a helpful customer service agent."},
-    {"role": "user", "content": "I want to cancel my subscription. My email is jane@example.com"}
-]
-
-# Agent loop
-while True:
-    response = client.chat.completions.create(
-        model=MODEL, messages=messages, tools=tools,
-        tool_choice="auto", temperature=0, max_tokens=1000
-    )
-    msg = response.choices[0].message
-
-    # Build assistant message — PRESERVE the reasoning field
-    assistant_msg = {"role": "assistant", "content": msg.content}
-    if msg.reasoning_content:
-        assistant_msg["reasoning"] = msg.reasoning_content  # ← critical for multi-turn
-    if msg.tool_calls:
-        assistant_msg["tool_calls"] = [
-            {"id": tc.id, "type": "function", "function": {"name": tc.function.name, "arguments": tc.function.arguments}}
-            for tc in msg.tool_calls
-        ]
-    messages.append(assistant_msg)
-
-    # If no tool calls, model gave its final response — done
-    if not msg.tool_calls:
-        print(f"Final response: {msg.content}")
-        break
-
-    # Execute tool calls and append results
-    for tc in msg.tool_calls:
-        result = execute_tool(tc.function.name, tc.function.arguments)
-        print(f"  Tool: {tc.function.name}({tc.function.arguments}) → {result}")
-        messages.append({"role": "tool", "tool_call_id": tc.id, "content": result})
-```
-
-Expected output:
-```
-  Tool: get_customer_by_email({"email": "jane@example.com"}) → {"customer_id": "C2001", ...}
-  Tool: cancel_subscription({"customer_id": "C2001", ...}) → {"success": true, ...}
-  Final response: Your subscription has been cancelled successfully.
-```
-
-The critical line is:
-```python
-assistant_msg["reasoning"] = msg.reasoning_content  # ← pass reasoning back as "reasoning"
-```
-
-The OpenAI SDK exposes the field as `reasoning_content` on the response object, but vLLM 0.18+ expects `reasoning` on input messages. The chat template then re-wraps it in `<think>...</think>` tags automatically.
+**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
 
@@ -340,32 +253,20 @@ print(response)
 
 ### API
 
-#### OpenRouter
-
-Available on [OpenRouter](https://openrouter.ai/) with full reasoning and tool calling support:
-
-```bash
-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?"
-      }
-    ]
-  }'
-```
-
-**Multi-turn with OpenRouter**: OpenRouter returns reasoning in a `reasoning_details` object (their unified reasoning shape). For multi-turn conversations, pass `reasoning_details` back as-is on assistant messages in subsequent requests — OpenRouter handles model-specific upstream translation (for Trinity, this is sent as `reasoning_content` on assistant turns upstream). For debugging, enable echo to inspect the upstream API call:
-
-```json
-{"debug": {"echo_upstream_body": true}}
-```
-
-See [OpenRouter debugging docs](https://openrouter.ai/docs/api/reference/errors-and-debugging#debugging) for details.
+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
 
@@ -375,8 +276,6 @@ Trinity-Large-Thinking is optimized for deployment as the reasoning backbone of
 
 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.
 
-**Deploying for OpenClaw users**: OpenClaw preserves full assistant turns across steps. For vLLM compatibility in public deployments, ensure the assistant reasoning is forwarded on the next turn as `reasoning` (not only `reasoning_content`) and keep assistant `content` non-null (empty string is fine). If your SDK emits `reasoning_content`, add a small adapter at your gateway to map it to `reasoning` before sending requests to vLLM.
-
 ### 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.
@@ -386,14 +285,12 @@ Compatible with the Hermes Agent framework from Nous Research. Trinity-Large-Thi
 For custom implementations, the key integration pattern is:
 
 1. Send the user message with tool definitions
-2. Receive the response with `reasoning` + `content` + `tool_calls`
+2. Receive the response with `<think>` reasoning + tool calls
 3. Execute the tool calls
-4. Append the **full** assistant response (reasoning + content + tool calls) and tool results to the message history
+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
 
-> **Important**: Step 4 must include the `reasoning` field on the assistant message. The chat template reads this field and re-wraps it in `<think>...</think>` tags during tokenization. Omitting it degrades multi-step performance — see [Preserving reasoning in multi-turn conversations](#preserving-reasoning-in-multi-turn-conversations) for details.
-
 ## License
 
 Trinity-Large-Thinking is released under the Apache License, Version 2.0.
@@ -402,15 +299,13 @@ Trinity-Large-Thinking is released under the Apache License, Version 2.0.
 
 If you use this model, please cite:
 
-```bibtex
-@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}
-}
-```
+    @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}
+    }