GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
prithivMLmods
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
prithivMLmods
Model Tree
google/gemma-4-E2B-it
Input Modalities
Output Modalities
Supported Functionality
Latest Transformers Compatibility Re-sharded and optimized for improved compatibility with recent Transformers releases.
Optimized Model Sharding Updated shard structure for better storage handling, download reliability, and inference efficiency.
Stable Inference Pipeline Improved packaging for consistent loading and generation behavior across environments.
E2B Architecture Built on gemma-4-E2B-it, offering efficient reasoning with low compute requirements.
Improved Deployment Stability Designed for smoother inference across diverse hardware configurations.
Preserved Model Behavior No modifications to weights or architecture; behavior remains consistent with the base model lineage.
This model has been re-sharded and optimized for the latest Transformers version from the base model: https://huggingface.co/huihui-ai/Huihui-gemma-4-E2B-it-abliterated
bash
pip install transformers==5.5.3# orpip install git+https://github.com/huggingface/transformers.gitpython
from transformers import Gemma4ForConditionalGeneration, AutoProcessorimport torch model = Gemma4ForConditionalGeneration.from_pretrained( "prithivMLmods/gemma-4-E2B-it-Uncensored-MAX", torch_dtype="auto", device_map="auto") processor = AutoProcessor.from_pretrained( "prithivMLmods/gemma-4-E2B-it-Uncensored-MAX") messages = [ { "role": "user", "content": [ {"type": "text", "text": "Explain how transformer models work in simple terms."} ], }] text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True) inputs = processor( text=[text], padding=True, return_tensors="pt").to("cuda") generated_ids = model.generate(**inputs, max_new_tokens=256) generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False) print(output_text)Multimodal and Language Research Studying efficiency-focused transformer behavior and inference dynamics.
Red-Teaming & Evaluation Testing robustness across edge-case and adversarial prompts.
Lightweight Deployment Running small-scale models on CPU or limited GPU environments.
Research Prototyping Experimentation with compact transformer architectures.
Important Note: This model inherits the behavior and limitations of its base architecture.
Output Variability Responses may vary depending on sampling configuration and prompt structure.
Resource Requirements While lightweight, GPU acceleration is recommended for best performance.
Deployment Constraints Performance depends on runtime optimization and hardware setup.
General Model Limitations May produce incorrect, incomplete, or inconsistent outputs in complex scenarios.
pip install transformers==5.5.3# orpip install git+https://github.com/huggingface/transformers.gitfrom transformers import Gemma4ForConditionalGeneration, AutoProcessorimport torch model = Gemma4ForConditionalGeneration.from_pretrained( "prithivMLmods/gemma-4-E2B-it-Uncensored-MAX", torch_dtype="auto", device_map="auto") processor = AutoProcessor.from_pretrained( "prithivMLmods/gemma-4-E2B-it-Uncensored-MAX") messages = [ { "role": "user", "content": [ {"type": "text", "text": "Explain how transformer models work in simple terms."} ], }] text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True) inputs = processor( text=[text], padding=True, return_tensors="pt").to("cuda") generated_ids = model.generate(**inputs, max_new_tokens=256) generated_ids_trimmed = [ out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)] output_text = processor.batch_decode( generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False) print(output_text)