GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
TianZhenkiseki
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
TianZhenkiseki
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
checkpoint_000060_loss_0.480.pthThe upstream checkpoint also contains projectors and multimodal pre-fusion weights. Those tensors are deliberately excluded here. No base-model weights are included.
Qwen/Qwen2.5-7B-Instructq_proj, k_proj, v_proj, o_proj, gate_proj,
down_proj, and up_proj in all 28 decoder layerspython
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase_id = "Qwen/Qwen2.5-7B-Instruct"adapter_id = "TianZhenkiseki/AffectGPT-Qwen2.5-7B-LoRA-epoch60"tokenizer = AutoTokenizer.from_pretrained(base_id)base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")model = PeftModel.from_pretrained(base, adapter_id)
For a fair A/B evaluation, use the same tokenizer, chat template, decoding settings, precision, and benchmark configuration for the base and adapted models. The text-only comparison measures the effect of AffectGPT's LoRA on the language backbone; it does not evaluate the complete multimodal system.
The converted Safetensors file contains 392 tensors: two LoRA matrices for seven target modules across 28 layers. Layer coverage, tensor count, rank, and parameter count were validated before upload.
The upstream repository includes an Apache-2.0 license file and additionally describes the service as a research preview intended for non-commercial use. Users should review and follow the upstream project's terms and notices.