GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mskm3266
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mskm3266
Model Tree
Qwen/Qwen3-8B-Base
Input Modalities
Output Modalities
Supported Functionality
transformerspython
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "mskm3266/uniform484_baseline_global_step_847" tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained( repo_id, torch_dtype=torch.bfloat16, device_map="auto",) prompt = "Solve: what is the remainder when 2^100 is divided by 7?"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))python
from vllm import LLM, SamplingParams llm = LLM(model="mskm3266/uniform484_baseline_global_step_847", dtype="bfloat16")out = llm.generate( ["Solve: what is the remainder when 2^100 is divided by 7?"], SamplingParams(temperature=0.7, top_p=0.95, max_tokens=512),)print(out[0].outputs[0].text)Or serve it:
bash
vllm serve mskm3266/uniform484_baseline_global_step_847 --dtype bfloat16bash
hf download mskm3266/uniform484_baseline_global_step_847 --local-dir ./uniform484_baseline_global_step_847chat_template.jinja inherited from the base model if you want it).import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "mskm3266/uniform484_baseline_global_step_847" tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained( repo_id, torch_dtype=torch.bfloat16, device_map="auto",) prompt = "Solve: what is the remainder when 2^100 is divided by 7?"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))from vllm import LLM, SamplingParams llm = LLM(model="mskm3266/uniform484_baseline_global_step_847", dtype="bfloat16")out = llm.generate( ["Solve: what is the remainder when 2^100 is divided by 7?"], SamplingParams(temperature=0.7, top_p=0.95, max_tokens=512),)print(out[0].outputs[0].text)