GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sm079
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
sm079
Model Tree
Qwen/Qwen3.5-0.8B-Base
Input Modalities
Output Modalities
Supported Functionality
On a held-out test set of 889 generated messages (95% CI from a scenario-group bootstrap):
| issue accuracy | clarification F1 | |
|---|---|---|
| keyword rules | 0.619 | 0.306 |
| Kev-0.8B, untouched | 0.425 | 0.182 |
| nepkev | 0.966 [0.953, 0.980] | 0.874 [0.797, 0.933] |
Fine-tuning adds +0.541 issue accuracy [+0.496, +0.588] over the untouched model on the same messages. By part of the test set (issue accuracy):
| untouched | fine-tuned | |
|---|---|---|
| clean Devanagari | 0.301 | 0.985 |
| Romanized | 0.420 | 0.952 |
| app-review style | 0.557 | 0.962 |
Issue ECE 0.021 after temperature calibration. No category is over-predicted (other at 1.03x its true share, precision 0.96).
About 7,400 labelled messages, balanced across categories: casual Devanagari, its Romanized twins, the same situations in app-review style, and a small set of labelled app reviews.
LoRA fine-tuning from jaredpalmer/kev-0.8b@9a45d25 with Kev 5e42a7a, 2 epochs (the epoch with the lowest dev
NLL is kept), temperature fitted on a calibration split.
A Kev checkpoint: adapter_model.safetensors is the LoRA adapter on Qwen/Qwen3.5-0.8B-Base@dc7cdfe,
head.pt holds the pointer head and the fitted temperature. With Kev at 5e42a7a:
bash
python -m kev.serve --run sm079/nepkev # POST /v1/systemoneThe request format (question wording and category descriptions per service) is in the code's
configs/taxonomy/demo-1.yaml.
onnx/ holds the same model for ONNX Runtime Web (WebGPU, or CPU through
WebAssembly). The adapter is merged into the backbone, which is exported without its language-model head so that it
outputs hidden states; head.bin is the pointer head (float32) and manifest.json lists the files and graph inputs.
Each question runs as one token row,
<|fim_prefix|> message <|fim_middle|> instruction (<|box_start|> option <|box_end|>)... <|fim_suffix|>, and the head
scores every option from the hidden states at <|fim_suffix|> and at each <|box_end|>.
| folder | download | answers that differ from full precision (240 test questions) | issue accuracy (108 test questions; full precision 0.972) |
|---|---|---|---|
onnx/int8 | 707 MB | 3 | 0.963 |
onnx/int8-fp16emb | 1,055 MB | 1 | 0.972 |
int8 also stores the embedding table in 4-bit blocks. 4-bit weights throughout cost about 5 points of issue accuracy
(0.917), so they are not published. A static demo page that runs these files is in the code's demo/ folder.
python -m kev.serve --run sm079/nepkev # POST /v1/systemone