GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
zzzekryo
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
zzzekryo
Model Tree
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Input Modalities
Output Modalities
Supported Functionality
A conversational language model based on TinyLlama, fine-tuned to balance concise replies, detailed explanations, and general assistance.
Oprius 3.0 is a fine-tuned version of TinyLlama 1.1B Chat. It aims to provide a natural conversational experience while adapting the length of its responses to the user's needs.
This release incorporates the trained LoRA adapter into the base model weights, allowing Oprius to be loaded as a standalone Transformers model without attaching the adapter separately.
Oprius aims to adapt its response length to the context rather than answering everything with the same amount of detail.
| Type of interaction | Intended response |
|---|---|
| Everyday conversation | Short and natural |
| General questions and assistance | Medium-length and useful |
| Complex concepts and elaborated explanations | Longer and more detailed |
| Web search requests | Search-oriented responses based on learned examples |
The goal is to keep simple conversations simple while providing more depth when a topic calls for it.
Oprius 3.1 includes training examples related to web search interactions.
These examples help the model learn how search requests and search-oriented responses may be structured. However, the model does not gain live internet access from fine-tuning alone.
To retrieve current information, Oprius must be connected to an external search tool or a compatible application that executes searches and provides the results to the model.
Without such an integration, its responses about current events and online information may be outdated or inaccurate.
Install the required libraries:
bash
pip install torch transformersLoad Oprius with Transformers:
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM model_id = "zzzekryo/Oprius-3.1-1.1B" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=( torch.float16 if torch.cuda.is_available() else torch.float32 ), device_map="auto",) messages = [ {"role": "user", "content": "yo, what is a GPU?"}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt",).to(model.device) with torch.inference_mode(): outputs = model.generate( inputs, max_new_tokens=150, do_sample=True, temperature=0.7, top_p=0.95, pad_token_id=tokenizer.eos_token_id, ) response = outputs[0][inputs.shape[-1]:] print(tokenizer.decode(response, skip_special_tokens=True))For reproducible outputs, use deterministic generation with do_sample=False. Sampling settings can affect response length, wording, and consistency.
This project is licensed under the Apache License 2.0.
In accordance with the Apache 2.0 license requirements, please note:
Oprius 3.1 is built upon the TinyLlama project and its open-source ecosystem.
We express our deepest gratitude to the creators and contributors of TinyLlama for their outstanding work and dedication to democratizing open-source language models.
During Model's testing, There has been issues that can possibly happen during usage:
On web searches, the model has been to noticeably repeating the system prompt in messages, when it shouldn't.
The model can generate short responses even for topics where it has been trained to elaborate.
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM model_id = "zzzekryo/Oprius-3.1-1.1B" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=( torch.float16 if torch.cuda.is_available() else torch.float32 ), device_map="auto",) messages = [ {"role": "user", "content": "yo, what is a GPU?"}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt",).to(model.device) with torch.inference_mode(): outputs = model.generate( inputs, max_new_tokens=150, do_sample=True, temperature=0.7, top_p=0.95, pad_token_id=tokenizer.eos_token_id, ) response = outputs[0][inputs.shape[-1]:] print(tokenizer.decode(response, skip_special_tokens=True))