Text Generation
Transformers
Safetensors
gemma4_unified
image-text-to-text
decision-making
multiple-choice
conversational
Instructions to use plantwaterer/muria with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use plantwaterer/muria with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="plantwaterer/muria") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("plantwaterer/muria") model = AutoModelForMultimodalLM.from_pretrained("plantwaterer/muria", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use plantwaterer/muria with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "plantwaterer/muria" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "plantwaterer/muria", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/plantwaterer/muria
- SGLang
How to use plantwaterer/muria with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "plantwaterer/muria" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "plantwaterer/muria", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "plantwaterer/muria" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "plantwaterer/muria", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use plantwaterer/muria with Docker Model Runner:
docker model run hf.co/plantwaterer/muria
Download vbll_head.json from plantwaterer/muria: direct link, hf CLI and curl.
- Browser
- Download file 2.49 kB
-
https://huggingface.co/plantwaterer/muria/resolve/main/vbll_head.json
- Command line
-
hf download hf://plantwaterer/muria/vbll_head.json
-
curl -L -o vbll_head.json https://huggingface.co/plantwaterer/muria/resolve/main/vbll_head.json
2.49 kB
| { | |
| "candidate": "l01post_di", | |
| "constants": { | |
| "alpha": 0.0, | |
| "beta": 0.25, | |
| "dnorm": "ratio", | |
| "infl": 10.0, | |
| "kern": 0.2, | |
| "lam": 1000.0, | |
| "lam_uni": 0.05, | |
| "nd": 512, | |
| "sig": 0.0, | |
| "sig_uni": 0.2, | |
| "tau": 0.3 | |
| }, | |
| "constants_source": "MACKAY-HEAD latent01_freeze.py e5d3e5be MK_DI=1, C-selected (pooled C 0.590183; tmp/mackay_head/sd12/latent01_frozen_di); kern / lam_uni / sig_uni = the full freeze's (they act only on the optional ordinal path)", | |
| "dim": 512, | |
| "draw_seed": 0, | |
| "gh_nodes": 16, | |
| "head_rule": "l01post_di", | |
| "heads": [ | |
| { | |
| "cov": "laplace (noul)", | |
| "prior": "N(0, I / 1000) on the noul residual", | |
| "rule": "l01post" | |
| } | |
| ], | |
| "hidden": 3840, | |
| "kinds": { | |
| "codes": { | |
| "choice": 0, | |
| "noul": 1, | |
| "score": 2 | |
| }, | |
| "from": "training: the manifest's kind (variant di: score -> choice); serving: the request's question type (choice / noul); score only on the engine's optional ordinal path (ordinal=True and q['ordinal'] true; never on the board)", | |
| "noul": "positions 0 / 1 = yes / no (the request's noul order)" | |
| }, | |
| "label_ids": [ | |
| 236776, | |
| 236799, | |
| 236780, | |
| 236796, | |
| 236788, | |
| 236811, | |
| 236823, | |
| 236814, | |
| 236777, | |
| 236863, | |
| 236855, | |
| 236798, | |
| 236792, | |
| 236797, | |
| 236806, | |
| 236791, | |
| 236935, | |
| 236794, | |
| 236773, | |
| 236774, | |
| 236836, | |
| 236847, | |
| 236824, | |
| 236917, | |
| 236874, | |
| 236953, | |
| 236746, | |
| 236763, | |
| 236755, | |
| 236753, | |
| 236744, | |
| 236760, | |
| 236759, | |
| 236754, | |
| 236747, | |
| 236804, | |
| 236767, | |
| 236752, | |
| 236757, | |
| 236749, | |
| 236748, | |
| 236758, | |
| 236809, | |
| 236750, | |
| 236751, | |
| 236745, | |
| 236756, | |
| 236766, | |
| 236765, | |
| 236781, | |
| 236762, | |
| 236802 | |
| ], | |
| "letters": "A-Z a-z (52, one token each)", | |
| "mode": "l01post_di", | |
| "native_logits": "fp32 h @ E[letters]^T with final_logit_softcapping (tied embedding)", | |
| "readout": "latent01_post: [0, 1] one-vs-rest S-curve sigma integral (16-node Gauss-Hermite) + score-interval integral", | |
| "refit": "sdv1_head v4.1 (2026-10-15; v4.0 + the Latent01 readout device-safe for CUDA serving; rules select | sdh | beta0 | p0beta | fixedE | lloc | l01post | l01post_di)", | |
| "rel_s": { | |
| "choice": 1.0, | |
| "noul": 1.1681289996539959, | |
| "score": 1.0 | |
| }, | |
| "res_mean": 2.9683754682073973, | |
| "samples": 0, | |
| "schema": "jev-l01post-head-v1", | |
| "temperature": 0.9695485629434267, | |
| "temperature_mode": "single", | |
| "temperature_semantics": "the Latent01-post readout at T (per-kind T_row = T (1 + tau (rel_s[kind] - 1)))", | |
| "tensor_sha256": "93ea4cbf3c040d9867cbf37e03b2869056ef74fe5f189255d578d3a056fa12e3", | |
| "variant": "di" | |
| } |