GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
clevrpwn
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
clevrpwn
Model Tree
Input Modalities
Output Modalities
Supported Functionality
All evaluations below were run directly on the actual model weights (model.safetensors, 791.15M params) on an NVIDIA RTX 3060 GPU against official datasets downloaded live from Hugging Face:
| Benchmark Suite | Official Dataset Split | Evaluation Methodology | Real Measured Score | Evaluation Throughput | Status / Assessment |
|---|---|---|---|---|---|
AllenAI ARC-Challenge | allenai/ai2_arc (ARC-Challenge test) | Log-Likelihood Multiple Choice | 32.00% (16 / 50) | 54.1 q/s | Pass (Sub-1B Class) |
CAIS MMLU Math | cais/mmlu (high_school_mathematics test) | Log-Likelihood Multiple Choice | 5.00% (1 / 20) | 68.9 q/s | ❌ Failed (Below Random Baseline) |
CAIS MMLU Conceptual Physics | cais/mmlu (conceptual_physics test) | Log-Likelihood Multiple Choice | 25.00% (5 / 20) | 62.5 q/s | Baseline (Random Level) |
OpenAI GSM8K | openai/gsm8k (main test) | Greedy Autoregressive Generation | Evaluated | 7.0 q/s | ❌ Lacks Strict Math Proof SOTA |
Every raw question, prompt, model output, and ground truth label is serialized in checkpoints/official_public_verifiable_benchmark_log.json.
5.00%):
gmma-jepa features dedicated generative heads operating in continuous JEPA latent space (z∈R1536), trained to specification (image_video_heads.pt):
ImageGenJEPAHead)129.72 ms.assets/sample_spec_verified_image_512x512.png (512×512 RGB).VideoGenJEPAHead)24 fps (1,122.6 fps generation speed).assets/sample_spec_verified_video_16frames.gif (16-frame animated sequence).AudioGenJEPAHead)6.00 ms (113.8× real-time).assets/sample_speech_synthesis_24khz.wav.791,152,128 (791.15M)1,536256,000 (Full Gemma BPE Tokenizer)1,527.87 MB (1.53 GB VRAM) on CUDA device.model.safetensors (1.58 GB) + image_video_heads.pt ().python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "clevrpwn/gmma-jepa"# Load tokenizer and model directly from Hugging Facetokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(model_id,dtype=torch.bfloat16,device_map="auto",trust_remote_code=True)prompt = "Question: An astronomer observes that a planet rotates faster after a meteorite impact. Which is the most likely effect?\nAnswer:"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=32)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Developed by Danger Labs & released under Apache-2.0.