GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
geonho1
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
geonho1
Model Tree
Base
mistralai/Mistral-7B-Instruct-v0.2
Adapter
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
mistralai/Mistral-7B-Instruct-v0.2Lots-of-LoRAs/task1215_atomic_classification_capableoftrainvalid1215atomic classification capableof64q_proj, k_proj, v_proj320.05none4bit-nf4QLoRA 4bit NF4, double quantization enabled, bf16 computefloat32plain5.0eval_loss0.0002cosineadapter_model.safetensors: LoRA adapter weightsadapter_config.json: PEFT adapter configurationtask_manifest.json: source manifest row and resolved splitstraining_protocol.json: fixed protocol used for this run0.0316paged_adamw_32bit