Update README.md

README.md

@@ -5,11 +5,114 @@ tags:
 - transformers
 - unsloth
 - qwen3_5
+- agent
 license: apache-2.0
 language:
 - en
 ---
 
+This model was trained on the following datasets using the qwen3.6 chat template (training was done with enable_thinking and preserve_thinking set to `True`):
+
+  - armand0e/badlogicgames-pi-mono-opus-filtered - Pi traces from Claude Opus (mainly 4.5)
+  - armand0e/kimi-k2.6-claude-code-traces - Claude Code traces from kimi k2.6
+  - armand0e/kimi-k2.6-agent - Codex traces from kimi k2.6
+  - armand0e/minimax-m2.7-agent - Pi traces from minimax m2.7
+  - TeichAI/Claude-Opus-4.6-Reasoning-887x (Downsampled to 200 examples, only present to stabilize chat behavior)
+
+Training specs:
+```
+MAX_SEQ_LEN = 49152
+
+from unsloth import FastModel
+import torch
+
+model = FastModel.get_peft_model(
+    model,
+    finetune_vision_layers     = False, # Turn off for just text!
+    finetune_language_layers   = True,  # Should leave on!
+    finetune_attention_modules = True,  # Attention good for GRPO
+    finetune_mlp_modules       = True,  # Should leave on always!
+
+    r = 64,           # Larger = higher accuracy, but might overfit
+    lora_alpha = 64,  # Recommended alpha == r at least
+    lora_dropout = 0,
+    bias = "none",
+    random_state = 3407,
+)
+
+from teich import prepare_data
+
+train_dataset = prepare_data(
+    {
+        "opus-agent": {
+            "source": "armand0e/badlogicgames-pi-mono-opus-filtered",
+        },
+        "kimi-claude": {
+            "source": "armand0e/kimi-k2.6-claude-code-traces",
+        },
+        "kimi-codex": {
+            "source": "armand0e/kimi-k2.6-agent",
+        },
+        "minimax-m2.7": {
+            "source": "armand0e/ag-datagen-v2-test",
+        },
+        "chat": {
+            "source": "TeichAI/Claude-Opus-4.6-Reasoning-887x",
+            "max_examples": 200,
+        }
+    },
+    tokenizer,
+    split="train",
+    hf_token=HF_TOKEN,
+    chat_template_kwargs={"enable_thinking": True, "preserve_thinking": True},
+    max_length=MAX_SEQ_LEN,
+    drop_oversized_examples=True,
+    trim_oversized_followups=True,
+    tokenize=True,
+    strict=True,
+)
+
+from trl import SFTConfig, SFTTrainer
+
+trainer = SFTTrainer(
+    model=model,
+    tokenizer=tokenizer,
+    train_dataset=train_dataset,
+    eval_dataset=None,
+    args=SFTConfig(
+        dataset_text_field="text",
+        dataset_num_proc=1,
+        max_length=MAX_SEQ_LEN,
+        packing=False,
+        per_device_train_batch_size=1,
+        gradient_accumulation_steps=8,
+        warmup_steps= 5,
+        num_train_epochs=2,
+        learning_rate=2e-4,
+        logging_steps=1,
+        save_steps=100,
+        save_total_limit=3,
+        optim="adamw_8bit",
+        weight_decay=0.01,
+        lr_scheduler_type="linear",
+        output_dir=OUTPUT_DIR,
+        seed=3407,
+        report_to="none",
+    ),
+)
+
+from teich import mask_data
+
+trainer = mask_data(
+    trainer,
+    tokenizer=tokenizer,
+    train_on_reasoning=True,
+    train_on_final_answers=True,
+    train_on_tools=True,
+)
+```
+
+---
 # Uploaded finetuned  model
 
 - **Developed by:** armand0e