GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
yinita
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
yinita
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
LoRA SFT on Qwen/Qwen3.5-4B with strict message_loss_mask over glm52 multitrack v2:
sft2_acquire (importance top-3 keys only, empty-content acquire_user_info) +
sft3_final_balanced (composite≥3, upsampled), history tool names canonicalized
(acquire_user_info / query_memory).
| Data | data/sft_splits/glm52_multitrack/sft_masked_train.jsonl (7232 rows) |
| Method | LoRA r=16 α=32, masked SFT |
| Epochs / lr | 3 / 1e-4 |
| Seq | 4096 |
Local path: results/0903/sft_mt_glm52_4b_v2
Uploaded: 2026-09-04T15:13:28.463966+00:00
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B", trust_remote_code=True)model = PeftModel.from_pretrained(base, "yinita/ps4mas-sft-mt-glm52-4b-v2")tok = AutoTokenizer.from_pretrained("yinita/ps4mas-sft-mt-glm52-4b-v2", trust_remote_code=True)