GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nbeerbower
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
nbeerbower
Model Tree
nbeerbower/BigBubba-Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
| Parameter | Value |
|---|---|
| Training Mode | ORPO |
| Base Model | nbeerbower/BigBubba-Qwen3.6-27B |
| Learning Rate | 8e-06 |
| Epochs | 2 |
| Batch Size | 2 |
| Gradient Accumulation | 4 |
| Effective Batch Size | 8 |
| Max Sequence Length | 2048 |
| Optimizer | paged_adamw_8bit |
| LR Scheduler | cosine |
| Warmup Ratio | 0.1 |
| Weight Decay | 0.01 |
| Max Grad Norm | 1.0 |
| Seed | 42 |
| Beta | 0.1 |
| Max Prompt Length | 1536 |
| LoRA Rank (r) | 32 |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.0 |
| Target Modules | up_proj, down_proj, gate_proj, k_proj, q_proj, v_proj, o_proj |
| GPU | NVIDIA GB10 |
Trained on 3 concatenated datasets:
nbeerbower/weasel-dpo (split: train)nbeerbower/seX-ai-dpo (split: train)nbeerbower/grok-politically-incorrect-dpo (split: train)This model was trained with Merlina. Credentials are not included — Merlina will use your own HF_TOKEN and WANDB_API_KEY from .env or the form.
Paste this code into Merlina's Load Configuration → From Code to rebuild the exact training setup:
text
merlina-config-v1:H4sIAOf1bGoC_81WS4_bRgz-K4s5247t3Ww3e8u2hwLNHoI2QIGiGFASJU08r8zDjrvY_15ypLGdNEGAIIfqRHEoDh8fP-pJSIMJOkgg7p-EBYPiXvz867tflm8PaK9Xt8vtTw9iITqMbVA-KWfJ4I8Ayio7XLXO9mrIAfjgKo4QsLvqgzNXcPWIQSsLy8TGpDauQ70iXwmGKO7_-nshYjuioZuFmWxfpNnxcnIsqoncY4jl7s2iGp91YrvarDbieSEaiCjLRaS1DWJo3AHDiwc1POSmgc-ycjn5nOTX087kTrtAIaaQcSFYlkHcX29nGbQf6fT2Zn7vgvPkVdyvV2vONAyYOKCskXMW2Usf3HuuqDvYKg-QsMq7Knyowr4KbhKocLNHmZyMsMepmiWABHEn09GXhF6_-_31G_nmkb7VCIErK6lXdHaHy_XtQthsJHrXjhTclsuX2lFG9Q-W1yFAp9AmCW2bTdalyzIm9GROGRv4KDXaIY1kvr65mzQUo_HpdLB5eX1bAkZd44KcHONgbnZpGKld8KxukMG4XlGnNTT0VTTOpZEM56oOYEyxeLkQysCAMmB0Ok_g3Ky3tRkB7O6iV9zMrjSzBx2pm0Z18hREBONLk6ZO80hETDwV0eXQ4lmqaYx5GOjLHuhwIQLVUaruU9wdkJzoZVcSi14rcjjlze8pIJiS1xzQSSMvO7FZ00Pghq5TnCNQSUogjKjvCCrin0tQPyKohWip7sZKA96Xb57E1H7yOAtkM7qIPKazwGG9xzYhx3USn58X35HLENxu6R3loFrQ-rhUtnUhkMv_X340or0LBgqoJqlmmtwOLd0b6GO00GiqASF-V-6cAMlDIztM5O2zs-c6XjOPfZv3fmBW7MwSExPLYYw0jFHWJOdBwi5TD9pCO3PJiw6JSZiMhuPpWnm6K2FMcydo5okK4pF4x1RymRmjV1pLJMXxa3RC8UXkkG-2Ezsxp0lLEVKLmUwOEAyRctlgM-vgnidsYrn1ajttgZuGYTTHz4oD2K6pSfocRybjMZ9UtKWGaXnIBqkkKKkMDrp6PvZsTQmpfSnNpMWP3lEthyH3p9v4RX7IYCe4lD3y9kb-Jh95FewQfbGXvd_cnlE95r4nGJ14bPJ_QDWMiXDUwrGWVgfJW5Y3SqiAbF2kpS0udgBZtDvvlE0XoNSuTGitFjlz9I9gGMnVkydMdJJ-McxB3nERmcjASKb5DYfw6kKxLYpXVUVOlS6kTuvqriiJDJILxPi8jfZYbj4lfT6PxAa0UiHQSCQaq_9azI0nyKQvnJYCzbtyuV59cnerlacRpKUzOt3NOIKUrFS8QgxVC-YfpXnTld8INVzEQX6IaloCs9LnuSjIKysWwjkq2rxJycHny4Epnp__BRCCRwLACQAA
Save this to data/configs/<name>.json, or import it via the Load Configuration dialog.
json
{"_metadata": {"name": "CHUD-Qwen3.6-27B","description": "Training configuration shared from a Merlina-trained model.","tags": [],"schema": "merlina/training-config","schema_version": 1,"merlina_version": "2.1.1"},"base_model": "nbeerbower/BigBubba-Qwen3.6-27B","output_name": "CHUD-Qwen3.6-27B","use_lora": true,"lora_r": 32,"lora_alpha": 64,"lora_dropout": 0.0,"target_modules": ["up_proj","down_proj","gate_proj","k_proj","q_proj","v_proj","o_proj"],"modules_to_save": [],"lora_task_type": "CAUSAL_LM","learning_rate": 8e-06,"num_epochs": 2,"batch_size": 2,"gradient_accumulation_steps": 4,"max_length": 2048,"max_prompt_length": 1536,"model_type": "auto","training_mode": "orpo","beta": 0.1,"label_smoothing": 0.0,"gamma": 0.5,"image_resolution": 1024,"lora_rank": 32,"lora_use_dora": false,"mid_training_samples": true,"dataset": {"source": {"source_type": "huggingface","repo_id": "nbeerbower/weasel-dpo","split": "train","streaming": false,"streaming_batch_size": 10000},"additional_sources": [{"source_type": "huggingface","repo_id": "nbeerbower/seX-ai-dpo","split": "train","streaming": false,"streaming_batch_size": 10000,"column_mapping": {"prompt": "prompt","chosen": "chosen","rejected": "rejected"}},{"source_type": "huggingface","repo_id": "nbeerbower/grok-politically-incorrect-dpo","split": "train","streaming": false,"streaming_batch_size": 10000,"column_mapping": {"prompt": "prompt","chosen": "chosen","rejected": "rejected"}}],"format": {"format_type": "tokenizer","enable_thinking": true,"auto_detect_thinking": true},"model_name": "nbeerbower/BigBubba-Qwen3.6-27B","column_mapping": {"prompt": "prompt","chosen": "chosen","rejected": "rejected"},"convert_messages_format": true,"deduplicate": false,"dedupe_strategy": "prompt_chosen","test_size": 0.01,"system_prompt_mode": "fill_empty","training_mode": "orpo"},"seed": 42,"max_grad_norm": 1.0,"warmup_ratio": 0.1,"eval_steps": 0.2,"use_4bit": false,"use_wandb": true,"push_to_hub": true,"merge_lora_before_upload": true,"hf_hub_private": true,"export_gguf": false,"gguf_quant_types": ["Q4_K_M"],"keep_gguf_fp16": false,"shuffle_dataset": true,"weight_decay": 0.01,"lr_scheduler_type": "cosine","gradient_checkpointing": true,"logging_steps": 1,"optimizer_type": "paged_adamw_8bit","adam_beta1": 0.9,"adam_beta2": 0.999,"adam_epsilon": 1e-08,"adafactor_relative_step": false,"adafactor_scale_parameter": false,"adafactor_warmup_init": false,"adafactor_decay_rate": -0.8,"adafactor_clip_threshold": 1.0,"attn_implementation": "auto","use_liger": false,"torch_compile": false,"eval_on_start": false,"multi_gpu_strategy": "auto"}
