GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
perletter
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
perletter
Model Tree
Input Modalities
Output Modalities
Supported Functionality
A small supervised fine-tune (~300 packed 512-token blocks: ~150 varied-phrasing
identity Q&A pairs + ~150 unrelated plain-text examples mixed in to guard against the
model overfitting into injecting its identity into unrelated answers) on top of
ckpt_best.pt, 15 epochs, low learning rate (2e-5), loss masked to the answer span only.
Honestly: partially, not perfectly. Tested on phrasings not seen during fine-tuning:
llama-cli) spot-check
using different default sampling settings than the direct-PyTorch tests failed to
recall the identity fact on one sample. The safetensors and GGUF weights are verified
byte-parity/near-parity identical (0.0 logit diff on export, <0.2% bpb quantization
delta) — this looks like ordinary sampling variance on an already-imperfect (not 100%)
fine-tune, not a quantization bug, but it means: don't expect this to work every
single time. Use lower temperature / greedy decoding for more consistent recall if
that matters for your use case.If you need this to be fully reliable rather than "mostly," that needs a larger/longer SFT pass than this one, which was intentionally kept small and disclosed as such.
Same as the base model — swap the repo name:
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("perletter/Dot-125M-Identity")model = AutoModelForCausalLM.from_pretrained("perletter/Dot-125M-Identity")prompt = "Q: What is your name?\nA:"inputs = tok(prompt, return_tensors="pt")out = model.generate(**inputs, max_new_tokens=30)print(tok.decode(out[0], skip_special_tokens=True))
bash
llama-cli -m model-Q8_0.gguf -p "Q: What is your name?\nA:" -n 30
Apache 2.0, same as the base model — see LICENSE. Training code not included.