GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
raspie
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
raspie
Model Tree
p-e-w/gemma-4-E2B-it-heretic-ara
Input Modalities
Output Modalities
Supported Functionality
원본 모델을 재배포하지 않고 LoRA만 제공합니다. 별도 LoRA 로더 노드는 사용하지 않습니다.
Load CLIP에 연결합니다. GGUF/mmproj는 이 경로에 사용할 수 없습니다.Gemma TIPO Native 또는 Gemma Prompt Expander Native 안의 **tipo_lora = pilot-001**를 선택합니다.none은 LoRA를 적용하거나 다운로드하지 않습니다.공유 자료에는 개인 이미지·VRS 경험·사전·학습 답안이 들어 있지 않습니다. 이름 보존, 한국어 제외 지시, 이미지 해석의 오류가 남아 있습니다. 새 이중 출력/VRS 기능의 성능 향상을 입증한 모델은 아닙니다.
c9a1d4c031981f14d86eeb0c7d87de7fafd34513.15605c16e479a8dc53928dd4b521a4ead9fe66222dc14d1ce392384e999a544b.Download that revision (using the website, or hf download p-e-w/gemma-4-E2B-it-heretic-ara --revision c9a1d4c031981f14d86eeb0c7d87de7fafd34513 --local-dir /path/to/base) then run the repository's existing converter:
bash
python scripts/prepare_gemma4_native.py --source /path/to/base --output /path/to/ComfyUI/models/text_encoders/gemma4-e2b-native-bf16.safetensorsIn Load CLIP, use type=stable_diffusion, device=default. The TIPO node handles its adapter internally using ComfyUI ModelPatcher. No PEFT, Transformers, bitsandbytes or llama.cpp is needed for native inference; PEFT format is preserved for other tools. No additional loader node or merged model download is needed. The full base is still required locally; an adapter does not replace it.
Offline: place adapter_config.json and adapter_model.safetensors in ComfyUI/models/loras/rs_gemma_tipo/pilot-001/ before running; the node checks published SHA-256 hashes. Other local files are not silently overwritten.
See native usage and installation and two output formats.
| Model | Raw condition passes / 100 | After tag cleanup / 100 | Specified names preserved / 245 |
|---|---|---|---|
| Base | 15 | 18 | 226 |
| Pilot 001 | 42 | 50 | 244 |
| Pilot 002 | 50 | 54 | 236 |
These are automatic tag-condition checks on the separately merged BF16 models, not human quality, character-identification or general language scores. Native runtime patching uses ComfyUI's weight/casting lifecycle; exact token-for-token parity with merged BF16 is not promised. Pilot 002 improved some expansion/edit checks but regressed on protected names and exclusions. Neither candidate is selected as the default.
training_summary.json contains sanitized provenance. Tensor bytes are unchanged from the original adapter. The release config replaces the private filesystem path with the public base and restores exact language-only target names from the training run.
Apache-2.0; see LICENSE and NOTICE. Upstream base/lineage model cards are linked above. This repository contains only adapter weights and documentation, not the base model or any personal source data.
python scripts/prepare_gemma4_native.py --source /path/to/base --output /path/to/ComfyUI/models/text_encoders/gemma4-e2b-native-bf16.safetensors