GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
philipjohnbasile
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
philipjohnbasile
Model Tree
Input Modalities
Output Modalities
Supported Functionality
bash
pip install "torch==2.13.0" "transformers==5.14.1"
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerrepo = "philipjohnbasile/wisp-coder-110m"revision = "186479fd8c1eb767e0d886014fb78b3426dc509a" # pinned weights/tokenizertokenizer = AutoTokenizer.from_pretrained(repo, revision=revision)model = AutoModelForCausalLM.from_pretrained(repo, revision=revision, dtype=torch.float32, trust_remote_code=False,).eval()inputs = tokenizer("def is_even(n):\n return ", return_tensors="pt", add_special_tokens=False)with torch.inference_mode():output = model.generate(**inputs, max_new_tokens=32, do_sample=False,pad_token_id=tokenizer.pad_token_id)print(tokenizer.decode(output[0], skip_special_tokens=True))
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel = AutoModelForCausalLM.from_pretrained("philipjohnbasile/wisp-coder-110m")tok = AutoTokenizer.from_pretrained("philipjohnbasile/wisp-coder-110m")print(tok.decode(model.generate(**tok("def quicksort(arr):", return_tensors="pt"),max_new_tokens=64)[0]))
python
# PSM: prefix, suffix, then generate the middleprompt = f"<|fim_prefix|>{prefix}<|fim_suffix|>{suffix}<|fim_middle|>"
python
import osimport sysfrom huggingface_hub import snapshot_downloadfrom tokenizers import Tokenizerpackage = snapshot_download("philipjohnbasile/wisp-coder-110m",local_dir=os.path.abspath("wisp-coder-110m-package"),)sys.path.insert(0, package)from wisp_mtp_reference import WispMTPReferenceRuntimetok = Tokenizer.from_file(os.path.join(package, "tokenizer.json"))ids = tok.encode(prompt, add_special_tokens=False).idsruntime = WispMTPReferenceRuntime.load(package)result = runtime.verify_greedy_parity(ids, max_new_tokens=16, depth=2)print(result["mtp_route"])
bibtex
@software{wisp_coder,title = {Wisp: fill-in-the-middle and native multi-token prediction in a small code model},year = {2026},url = {https://huggingface.co/philipjohnbasile/wisp-coder-110m}}