GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Aquiles-ai
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
Aquiles-ai
Model Tree
huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
Input Modalities
Output Modalities
Supported Functionality
Athenea-4B-Thinking leverages the structured reasoning framework of Huihui-Qwen3 and expands it across multiple domains and languages. It serves as a multidomain reasoning model, performing well in both conversational and analytical contexts.
Key features:
<think> blocksThe model was fine-tuned using the dataset Aquiles-ai/Athenea-40k.
Note: Fine-tuning was performed using Kronos, Aquiles-ai’s proprietary enterprise fine-tuning system.
bash
uv pip install transformers torch acceleratepython
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") # Requires flash-attn # Without flash-attn:# model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Thinking",# dtype="auto",# device_map="auto"# ) tokenizer = AutoTokenizer.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", trust_remote_code=True)messages = [ {"role": "user", "content": "Hey, explain to me in simple terms how reinforcement learning works."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=8092, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id, ) # Decode and print the outputprint(tokenizer.decode(output[0], skip_special_tokens=True))python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamerimport torchfrom threading import Thread model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") tokenizer = AutoTokenizer.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", trust_remote_code=True) messages = [ {"role": "user", "content": "Hey, explain the difference between artificial intelligence, machine learning, and deep learning."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') # Create the streamerstreamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Build kwargs for generategenerate_kwargs = dict( **inputs, max_new_tokens=8092, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id, streamer=streamer,) def _generate_thread(model, kwargs): with torch.no_grad(): model.generate(**kwargs) thread = Thread(target=_generate_thread, args=(model, generate_kwargs)) thread.start() for chunk in streamer: print(chunk, end="", flush=True)Start server:
bash
vllm serve Aquiles-ai/Athenea-4B-Thinking \ --host 0.0.0.0 \ --port 8000 \ --api-key dummyapikey \ --max-model-len=16384 \ --async-scheduling \ --gpu-memory-utilization=0.90Request to the server from the OpenAI client:
python
from openai import OpenAI client = OpenAI(api_key="dummyapikey", base_url="http://127.0.0.1:8000/v1") stream = client.chat.completions.create( model="Aquiles-ai/Athenea-4B-Thinking", messages=[{ "role": "user", "content": "Hey, tell me how a large language model like Llama or GPT is trained." }], max_tokens=8092, stream=True) for chunk in stream: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="", flush=True)vLLM Benefits: 20-30x faster inference, OpenAI-compatible API, continuous batching, async scheduling.
In addition to code usage, you can also try our models locally through an open-source playground on GitHub.
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") # Requires flash-attn # Without flash-attn:# model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Thinking",# dtype="auto",# device_map="auto"# ) tokenizer = AutoTokenizer.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", trust_remote_code=True)messages = [ {"role": "user", "content": "Hey, explain to me in simple terms how reinforcement learning works."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=8092, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id, ) # Decode and print the outputprint(tokenizer.decode(output[0], skip_special_tokens=True))from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamerimport torchfrom threading import Thread model = AutoModelForCausalLM.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", attn_implementation="flash_attention_2") tokenizer = AutoTokenizer.from_pretrained("Aquiles-ai/Athenea-4B-Thinking", trust_remote_code=True) messages = [ {"role": "user", "content": "Hey, explain the difference between artificial intelligence, machine learning, and deep learning."}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt",).to('cuda') # Create the streamerstreamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Build kwargs for generategenerate_kwargs = dict( **inputs, max_new_tokens=8092, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id, streamer=streamer,) def _generate_thread(model, kwargs): with torch.no_grad(): model.generate(**kwargs) thread = Thread(target=_generate_thread, args=(model, generate_kwargs)) thread.start() for chunk in streamer: print(chunk, end="", flush=True)vllm serve Aquiles-ai/Athenea-4B-Thinking \ --host 0.0.0.0 \ --port 8000 \ --api-key dummyapikey \ --max-model-len=16384 \ --async-scheduling \ --gpu-memory-utilization=0.90from openai import OpenAI client = OpenAI(api_key="dummyapikey", base_url="http://127.0.0.1:8000/v1") stream = client.chat.completions.create( model="Aquiles-ai/Athenea-4B-Thinking", messages=[{ "role": "user", "content": "Hey, tell me how a large language model like Llama or GPT is trained." }], max_tokens=8092, stream=True) for chunk in stream: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="", flush=True)