GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CompiwerAI
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
CompiwerAI
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Mtrini-SVL-1.1 is an open-weight ~8B model developed by Compiwer AI, based on Qwen3-VL-8B-Instruct.
It was trained with a focus on:
And yes...
It's a Mtrini. 🐪
SVL = Self-Verifying Loop
Our development concept:
text
THINK ↓CHECK ↓IMPROVE ↓REPEAT 🔄 The goal is to encourage the model to verify and refine its responses. SVL is an ongoing research direction at Compiwer AI. 📚 Training The final dataset contained 58,574 unique examples. Dataset Examples🇲🇦 Moroccan Darija QA + Reasoning 2,170💻 OpenCodeReasoning-2 30,000🧮 OpenMathInstruct-2 30,000⚡ Model SpecsProperty ValueModel Mtrini-SVL-1.1Base Qwen3-VL-8B-InstructParameters ~8BArchitecture Qwen3-VLTraining LoRA / PEFTPrecision BF16Training Context 4096 tokensDataset 58,574 unique examplesDeveloper Compiwer AIOrigin 🇲🇦 Salé, Morocco📊 Training RunSteps: 3,661Epochs: 1Training Loss: 0.5855Mean Token Accuracy: 83.55% These metrics describe the training run and should not be treated as standardized benchmark scores. 🚀 Usagefrom transformers import Qwen3VLForConditionalGeneration, AutoTokenizer model_id = "CompiwerAI/Mtrini-SVL-1.1-Merged" tokenizer = AutoTokenizer.from_pretrained( model_id, trust_remote_code=True) model = Qwen3VLForConditionalGeneration.from_pretrained( model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True)⚠️ Limitations Mtrini is an experimental open model. It can hallucinate, generate incorrect code, misunderstand prompts, or produce incorrect mathematical answers. Verify important outputs. 🌍 Why Mtrini? AI shouldn't only be built by the biggest companies on Earth. Mtrini is Compiwer AI's experiment in building open AI with a focus on: 🇲🇦 Moroccan language🧠 Reasoning💻 Coding🧮 Mathematics🤝 Open AI Building AI For Everyone. Built in Salé, Morocco 🇲🇦THINK ↓CHECK ↓IMPROVE ↓REPEAT 🔄The goal is to encourage the model to verify and refine its responses.SVL is an ongoing research direction at Compiwer AI.📚 TrainingThe final dataset contained 58,574 unique examples.Dataset Examples🇲🇦 Moroccan Darija QA + Reasoning 2,170💻 OpenCodeReasoning-2 30,000🧮 OpenMathInstruct-2 30,000⚡ Model SpecsProperty ValueModel Mtrini-SVL-1.1Base Qwen3-VL-8B-InstructParameters ~8BArchitecture Qwen3-VLTraining LoRA / PEFTPrecision BF16Training Context 4096 tokensDataset 58,574 unique examplesDeveloper Compiwer AIOrigin 🇲🇦 Salé, Morocco📊 Training RunSteps: 3,661Epochs: 1Training Loss: 0.5855Mean Token Accuracy: 83.55%These metrics describe the training run and should not be treated as standardized benchmark scores.🚀 Usagefrom transformers import Qwen3VLForConditionalGeneration, AutoTokenizermodel_id = "CompiwerAI/Mtrini-SVL-1.1-Merged"tokenizer = AutoTokenizer.from_pretrained( model_id, trust_remote_code=True)model = Qwen3VLForConditionalGeneration.from_pretrained( model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True)⚠️ LimitationsMtrini is an experimental open model.It can hallucinate, generate incorrect code, misunderstand prompts, or produce incorrect mathematical answers.Verify important outputs.🌍 Why Mtrini?AI shouldn't only be built by the biggest companies on Earth.Mtrini is Compiwer AI's experiment in building open AI with a focus on:🇲🇦 Moroccan language🧠 Reasoning💻 Coding🧮 Mathematics🤝 Open AIBuilding AI For Everyone.Built in Salé, Morocco 🇲🇦