GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Occupying-Mars
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
Occupying-Mars
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
LoRA adapter for Qwen/Qwen3-8B, trained for the circuit-shotting BFCL single-call experiments.
Run details:
data/bfcl_strict_10k_mix/train.jsonlruns/issue49_bfcl_single_call/relp_full.npz160000 MLP channels32641024runs/issue49_bfcl_single_call/lora_bfcl10k_topk160000_r32_balanced_len1024_ckptEval on the 1007-row BFCL single-turn/single-call slice, with canonicalization prompt and normalized exact matching:
| condition | score |
|---|---|
| unmasked merged model | 683/1007 = 67.83% |
| k160 masked merged model | 418/1007 = 41.51% |
Included files:
adapter_model.safetensors: PEFT LoRA adapter weightsadapter_config.json: PEFT adapter configtokenizer.json, tokenizer_config.json, chat_template.jinja: tokenizer artifactstrain_summary.json: training summaryeval_masked_summary.json: k160 masked eval summaryeval_unmasked_summary.json: unmasked eval summary