Any-to-Any
Transformers
Safetensors
GGUF
gemma4
multimodal
text-generation
image-text-to-text
audio-text-to-text
video-text-to-text
long-context
lora
bf16
llama-cpp
zh
en
Instructions to use chirs345678/Anrn-12B-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use chirs345678/Anrn-12B-R1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("chirs345678/Anrn-12B-R1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Invalid JSON:Unexpected token '', "{
"vari"... is not valid JSON
| { | |
| "variant": "full-bf16-original", | |
| "alias": "anru-gemma4-12b-native-multimodal-bf16-lora045", | |
| "max_gpu_memory": "14GiB", | |
| "composition": "byte-identical original BF16 base plus LoRA at scale 0.45", | |
| "attention_implementation": "sdpa", | |
| "default_system_prompt": "system_prompt.md", | |
| "system_prompt_source_name": "Anru_Constitution_v2_30000.md", | |
| "system_prompt_sha256": "5591AC2C99FDC6C8E21D1D3B87625BB368204548BEC7B63C3FD6598CF23639BF", | |
| "system_prompt_bytes": 105352, | |
| "system_prompt_chars": 38029, | |
| "system_prompt_lines": 1984, | |
| "llama_service": { | |
| "launcher": "Start-Llama-Service.bat", | |
| "bootstrap": "llama-bootstrap.ps1", | |
| "runtime": "bundled when packaged; downloads latest official llama.cpp Windows build if missing", | |
| "gguf_model": "llama-model/anru-gemma4-12b-base-Q5_K_M.gguf", | |
| "gguf_lora": "llama-model/anru-final-lora-Q8_0.gguf", | |
| "lora_scale": 0.45, | |
| "context_tokens": 131072, | |
| "web_ui": "http://127.0.0.1:8091", | |
| "prompt_embedded_in_template": true, | |
| "prompt_sha256": "5591AC2C99FDC6C8E21D1D3B87625BB368204548BEC7B63C3FD6598CF23639BF", | |
| "mode": "llama.cpp text Web UI; native start.ps1 retains text/image/audio/video" | |
| } | |
| } | |