GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
hotdogs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
hotdogs
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
| metric | value |
|---|---|
| base model | Qwen/Qwen3.8-27B |
| source model | perplexity-ai/pplx-decider-v1.1-27b |
| tensor pairs | 496 |
| rank | 64 |
| energy retained (mean) | 0.4546 |
| energy retained (min) | 0.1457 |
| energy retained (max) | 1.0000 |
| reconstruction rel. err (mean) | 0.6605 |
Note: the source model's delta is broad/diffuse, so rank-64 retains a modest mean energy (≈0.45).
in_proj_a/in_proj_b(GDN gates) and 1-D norm / 3-D conv1d tensors are excluded from the GGUF (see below) but are present in the full PEFT adapter.
adapter_model.safetensors — full PEFT/LoRA adapter (496 pairs, float32)adapter_config.json — PEFT config (target modules auto-derived)extraction_stats.json — per-tensor SVD metricspplx_decider_qwen3.8-27B_svd_lora.gguf — llama.cpp GGUF LoRA (800 tensors, ~1.7 GB)bash
llama-cli \ -m /path/to/Qwen3.8-27B.gguf \ --lo-ra pplx_decider_qwen3.8-27B_svd_lora.gguf 1.0 \ -p "Hello!"python
from transformers import AutoModelForCausalLMfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.8-27B", torch_dtype="auto")model = PeftModel.from_pretrained(base, "hotdogs/qwen3.8-27B-pplx-decider_svd_lora")The GGUF contains 800 tensors. in_proj_a / in_proj_b (GDN gates) are
excluded because convert_lora_to_gguf.py does not map those GDN gate
names; 1-D norm weights and 3-D conv1d are not LoRA-able and are omitted. The
full PEFT adapter retains all 496 pairs.
Generated by exact truncated SVD on the weight difference
pplx-decider-v1.1-27b − Qwen3.8-27B. Target keys were remapped
(language_model.* → model.language_model.*) to align with the base model
key space.
llama-cli \ -m /path/to/Qwen3.8-27B.gguf \ --lo-ra pplx_decider_qwen3.8-27B_svd_lora.gguf 1.0 \ -p "Hello!"from transformers import AutoModelForCausalLMfrom peft import PeftModel base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.8-27B", torch_dtype="auto")model = PeftModel.from_pretrained(base, "hotdogs/qwen3.8-27B-pplx-decider_svd_lora")