GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
KrynexLabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
KrynexLabs
Model Tree
SupraLabs/Supra2.1-Ultra
Input Modalities
Output Modalities
Supported Functionality
KrynexAI 1.5 is the model that refers to the KrynexAI Main family. It has 250M params, 40B tokens trained on, with LLaMa arch. It is a small base model that is probably going to generate incorrect or biased text, and it has neither been aligned nor evaluated for safety.
| Spec | Details |
|---|---|
| Parameters | 250M |
| Tokens seen | ~40.4B |
| Arch | Llama |
| Layers | 32 |
| Hidden size | 768 |
| Intermediate size (MLP) | 1920 |
| Attention heads | 12 (head dim 64) |
| KV heads (GQA) | 4 |
| Vocabulary size | 49,152 |
| Context length | 2,048 |
| RoPE theta | 10,000 |
| Activation | SiLU (SwiGLU MLP) |
| Tied embeddings | Yes |
| Precision | bfloat16 |
This model was trained on a single A100 SXM.
| Benchmark | Shots | acc | acc_norm | Random |
|---|---|---|---|---|
| HellaSwag | 0 | 31.64 | 37.18 | 25.0 |
| PIQA | 0 | 65.78 | 64.91 | 50.0 |
| ARC-Easy | 0 | 57.11 | 50.46 | 25.0 |
| ARC-Challenge | 0 | 25.00 | 26.28 | 25.0 |
| Arithmark-v3 | 0 | 38.00 | 38.20 | - |
| Open SLM leaderboard's II | - | 20.64 | - | - |
This code should download the model and generate a response.
bash
pip install transformerspython
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMcheckpoint = "KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile"device = "cuda" if torch.cuda.is_available() else "cpu"tokenizer = AutoTokenizer.from_pretrained(checkpoint)model = AutoModelForCausalLM.from_pretrained( checkpoint, torch_dtype=torch.bfloat16, device_map="auto")inputs = tokenizer.encode("Gravity is", return_tensors="pt").to(device)outputs = model.generate(inputs, max_new_tokens=50)print(tokenizer.decode(outputs[0], skip_special_tokens=True))This model is released under Apache-2.0 License — you can use, modify, and share this code freely, even in commercial projects. The only requirement is to keep the original attribution. Full text in the file: LICENSE.
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMcheckpoint = "KrynexLabs/KrynexAI-1.5-250M-Instruct-Mobile"device = "cuda" if torch.cuda.is_available() else "cpu"tokenizer = AutoTokenizer.from_pretrained(checkpoint)model = AutoModelForCausalLM.from_pretrained( checkpoint, torch_dtype=torch.bfloat16, device_map="auto")inputs = tokenizer.encode("Gravity is", return_tensors="pt").to(device)outputs = model.generate(inputs, max_new_tokens=50)print(tokenizer.decode(outputs[0], skip_special_tokens=True))