GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Mwanzau
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
Mwanzau
Model Tree
unsloth/Llama-3.2-1B-Instruct
Input Modalities
Output Modalities
Supported Functionality
To load these adapters on top of the base model using unsloth or standard Hugging Face Transformers:
python
import torchfrom unsloth import FastLanguageModel # 1. Load Base Model & Attach Adaptersmodel, tokenizer = FastLanguageModel.from_pretrained( model_name = "Mwanzau/Mazgu_Llama-1B-V2", # Automatically fetches base + adapters max_seq_length = 2048, load_in_4bit = True,) FastLanguageModel.for_inference(model) # 2. Formulate Prompt (Alpaca / Instruction Format)prompt = """### Instruction:Longosolani vyakurya ivyo vili bwino ku munda. ### Response:""" inputs = tokenizer([prompt], return_tensors="pt").to("cuda") # 3. Generateoutputs = model.generate( **inputs, max_new_tokens = 150, temperature = 0.6, repetition_penalty = 1.2) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ### 🏋️ Training ParametersFramework: Unsloth / PEFTRank ($r$): 16Alpha ($\alpha$): 16Training Steps: 500 Knowledge-SFT stepsDataset Format: Alpaca Instruction-Response (### Instruction: / ### Response:)Focus: Grounded domain factual recall (Agriculture, literature, Tumbuka linguistics).