GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
PraveenAIML
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
PraveenAIML
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen2.5-0.5B-Instruct at commit 7ae557604adf67be50417f59c2c2f167def9a775Qwen/Qwen2.5-0.5B-Instruct at commit 7ae557604adf67be50417f59c2c2f167def9a775Intel/orca_dpo_pairs at commit 624952e3f420ae18d88b31977ee2ea436c833abbThis adapter uses QLoRA fine-tuning and DPO preference alignment. It is not PPO-RLHF, does not include a separate reward model, and does not merge or publish full base-model weights.
json
{"alpha": 32,"dropout": 0.05,"rank": 16,"target_modules": ["q_proj","k_proj","v_proj","o_proj","gate_proj","up_proj","down_proj"]}
json
{"beta": 0.1,"bf16": false,"epochs": 1,"eval_steps": 100,"eval_strategy": "steps","fp16": true,"gradient_accumulation_steps": 8,"gradient_checkpointing": true,"learning_rate": 1e-05,"logging_steps": 10,"max_length": 1024,"per_device_eval_batch_size": 1,"per_device_train_batch_size": 1,"save_steps": 100,"save_strategy": "steps","save_total_limit": 2}
json
{"do_sample": false,"max_new_tokens": 128,"temperature": 0.0}
Total adapter artifact size: 17642272 bytes (16.824982 MB)
ADAPTER_EXPORT_METADATA.json: 359 bytes (0.000342 MB)adapter_config.json: 1105 bytes (0.001054 MB)adapter_model.safetensors: 17640808 bytes (16.823586 MB)Intel/orca_dpo_pairs, not feedback collected by this project.adapter_manifest.json.