GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
FlameF0X
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
FlameF0X
Model Tree
FlameF0X/TinyMoE-200m-2x16
Input Modalities
Output Modalities
Supported Functionality
Important: This model does not have an embedded chat template. To ensure high-quality responses, you must manually format your prompts to match the structure used during training.
The model expects the following turn-based structure:
text
User: [Your message here]Assistant:
For multi-turn conversations, use:
text
User: [User message 1]Assistant: [Model response 1]User: [User message 2]Assistant:
python
from transformers import AutoTokenizer, AutoModelForCausalLMmodel_id = "FlameF0X/TinyChat-200m-2x16"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id)prompt = "User: Explain how MoE works.\nAssistant:"inputs = tokenizer(prompt, return_tensors="pt")outputs = model.generate(**inputs, max_new_tokens=100)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
This model was fine-tuned on the following datasets using LoRA:
Preprocessing: All datasets were converted to a standard messages format and rendered into the simple User: ... / Assistant: ... text style shown above.
Training Specs:
transformers + peft