GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
FurkanNar
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
FurkanNar
Model Tree
openai-community/gpt2
Input Modalities
Output Modalities
Supported Functionality
The model showed consistent improvement across epochs, with training loss decreasing from 0.7349 to 0.6216, indicating effective learning of the instruction-following task.
config.json - Model configurationgeneration_config.json - Generation parametersmodel.safetensors - Fine-tuned model weights (475MB)The application uses the official Alpaca instruction format for inference:
text
Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:{user_input} ### Response:Example interaction with the fine-tuned model:
text
You: HelloAI: Hi there! How can I help you today?The model generation can be configured with the following parameters:
model_name: Hugging Face model identifier or local pathsystem_prompt: System prompt for the assistantmax_length: Maximum response lengthtemperature: Sampling temperature (default: 0.5)top_k: Top-k sampling parameter (default: 40)top_p: Nucleus sampling parameter (default: 0.9)repetition_penalty: Penalty for repeating tokens (default: 1.2)Below is an instruction that describes a task. Write a response that appropriately completes the request.### Instruction:{user_input}### Response: