GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AhiskaAI
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
AhiskaAI
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Our research lab follows a strict vertical integration philosophy:
LlamaForCausalLM from zero variables. Pre-trained on 5.3 GB of clean Turkish text matrix to lock down grammar, token-nesting patterns, and core semantics (AhıskaAI 65m Base v0.1).1. 2. 3.), and multi-turn response compliance.Directly extracted from the native config.json, the model utilizes a pure modern LLaMA layout optimized for fast local compute:
LlamaForCausalLMmax_position_embeddings): 1024 tokens (Double the capacity of legacy GPT-2 baselines)hidden_size): 512intermediate_size): 1376num_hidden_layers): 12num_attention_heads / num_key_value_heads)silu)rms_norm_eps: 1e-06 (RMSNorm architecture)rope_type: default, theta: 10000.0)float32To interact with the instruction-tuned layer smoothly, invoke the model with the exact token structure it was aligned with:
python
from transformers import LlamaForCausalLM, AutoTokenizerimport torch model_name = "AhiskaAI/AhiskaAI-65m-IT-v0.1" # Load the custom-built architecture and vocabularymodel = LlamaForCausalLM.from_pretrained(model_name).to("cuda" if torch.cuda.is_available() else "cpu")tokenizer = AutoTokenizer.from_pretrained(model_name) def ask_ahiska_it(instruction): # Strict Alpaca Template prompt = f"<|im_start|>user\n{user_input}<|im_end|>\n<|im_start|>assistant\n" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_length=250, do_sample=True, top_k=40, top_p=0.92, temperature=0.55, # Low temp keeps the 65m nodes highly focused repetition_penalty=1.18 ) response = tokenizer.decode(outputs[0], skip_special_tokens=True) return response.split("### Response:\n")[-1].strip() # Run a test inferenceprint(ask_ahiska_it("Sağlıklı yaşamak için 3 ipucu ver"))from transformers import LlamaForCausalLM, AutoTokenizerimport torch model_name = "AhiskaAI/AhiskaAI-65m-IT-v0.1" # Load the custom-built architecture and vocabularymodel = LlamaForCausalLM.from_pretrained(model_name).to("cuda" if torch.cuda.is_available() else "cpu")tokenizer = AutoTokenizer.from_pretrained(model_name) def ask_ahiska_it(instruction): # Strict Alpaca Template prompt = f"<|im_start|>user\n{user_input}<|im_end|>\n<|im_start|>assistant\n" inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_length=250, do_sample=True, top_k=40, top_p=0.92, temperature=0.55, # Low temp keeps the 65m nodes highly focused repetition_penalty=1.18 ) response = tokenizer.decode(outputs[0], skip_special_tokens=True) return response.split("### Response:\n")[-1].strip() # Run a test inferenceprint(ask_ahiska_it("Sağlıklı yaşamak için 3 ipucu ver"))