Text Generation
Transformers
Safetensors
gemma4
image-text-to-text
decision-making
multiple-choice
conversational
Instructions to use plantwaterer/haimation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use plantwaterer/haimation with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="plantwaterer/haimation") 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/haimation") model = AutoModelForMultimodalLM.from_pretrained("plantwaterer/haimation", 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/haimation with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "plantwaterer/haimation" # 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/haimation", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/plantwaterer/haimation
- SGLang
How to use plantwaterer/haimation 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/haimation" \ --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/haimation", "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/haimation" \ --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/haimation", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use plantwaterer/haimation with Docker Model Runner:
docker model run hf.co/plantwaterer/haimation
Download PINS.json from plantwaterer/haimation: direct link, hf CLI and curl.
- Browser
- Download file 6.34 kB
-
https://huggingface.co/plantwaterer/haimation/resolve/main/PINS.json
- Command line
-
hf download hf://plantwaterer/haimation/PINS.json
-
curl -L -o PINS.json https://huggingface.co/plantwaterer/haimation/resolve/main/PINS.json
6.34 kB
| { | |
| "arm": "H1", | |
| "bundle_files": [ | |
| "DATA_NOTICE", | |
| "NOTICE", | |
| "config.json", | |
| "haimation/__init__.py", | |
| "haimation/attention.py", | |
| "haimation/balanced.py", | |
| "haimation/binary.py", | |
| "haimation/engine.py", | |
| "haimation/gate.py", | |
| "haimation/gate_long.py", | |
| "haimation/heads.py", | |
| "haimation/labels.json", | |
| "haimation/labels.py", | |
| "haimation/orders.py", | |
| "haimation/prompting.py", | |
| "haimation/readout.py", | |
| "haimation/render.py", | |
| "haimation/route.py", | |
| "haimation/runtime.py", | |
| "haimation/serving.py", | |
| "haimation/store/__init__.py", | |
| "haimation/store/lm/__init__.py", | |
| "haimation/store/lm/graph.py", | |
| "haimation/store/lm/kernels.py", | |
| "haimation/store/lm/memlm.py", | |
| "haimation/store/lm/modules.py", | |
| "haimation/store/numbers.py", | |
| "haimation/store/reader.py", | |
| "haimation/store/table.py", | |
| "haimation/text.py", | |
| "haimation/xr_runtime/LICENSE", | |
| "haimation/xr_runtime/NOTICE", | |
| "haimation/xr_runtime/SHA256SUMS", | |
| "haimation/xr_runtime/xr/__init__.py", | |
| "haimation/xr_runtime/xr/base.py", | |
| "haimation/xr_runtime/xr/cc.py", | |
| "haimation/xr_runtime/xr/front.py", | |
| "haimation/xr_runtime/xr/gpu.fatbin", | |
| "haimation/xr_runtime/xr/gpu.fatbin.json", | |
| "haimation/xr_runtime/xr/gpu.py", | |
| "haimation/xr_runtime/xr/isa.py", | |
| "haimation/xr_runtime/xr/ops.py", | |
| "haimation/xr_runtime/xr/ref.py", | |
| "haimation/xr_runtime/xr/score.py", | |
| "head.json", | |
| "head.safetensors", | |
| "store_block.json", | |
| "store_block.safetensors", | |
| "store_table.json", | |
| "PINS.json" | |
| ], | |
| "candidate": "H1: haimation:Engine, the model's own head, executed answers at 0.925 / 0.75", | |
| "checkpoint": { | |
| "config_md5": "531c1010635329e30e9a8ca4b511221b", | |
| "export_identity_sha256": "58582eb505a750034e7d2864e71ae2da649ccdb4b959dce2cf0c4331e4b72262" | |
| }, | |
| "choice_head": null, | |
| "engine_class": "haimation:Engine", | |
| "executor_backend": "auto", | |
| "executor_runtime": "xr 1.1.0 (tgz 6adf1df8341fff6f54940e551c9ddf2a), backend auto", | |
| "kit": "decision-index 9eb2dbe2a358004c8782c66e40a83ac07b953fec (kit tgz md5 1ec1274c)", | |
| "memory_files": { | |
| "store_block.json": "397978673fb8d7697eabaeb51471a525", | |
| "store_block.safetensors": "8a90825ccb3df324b95e464b65437321", | |
| "store_table.json": "263e33e4961f9d0d85cd1bc5a7bcb52b" | |
| }, | |
| "noul_head": { | |
| "file": "head.json", | |
| "json_md5": "7415d7b5607a364b54f950d146dfcf02", | |
| "mode": "binary", | |
| "schema": "binary-laplace-head-v1", | |
| "temperature": 1.2984044496188827, | |
| "tensor_sha256": "9e8a728457db385e7de92d04648a9f74f34859a01c2239c95c086e5414bbfcb9" | |
| }, | |
| "package_files": { | |
| "DATA_NOTICE": "0710fa29b21434f0397007632cb9770f", | |
| "NOTICE": "de7577cbdaecba0be104c151a18f1b65", | |
| "config.json": "531c1010635329e30e9a8ca4b511221b", | |
| "haimation/__init__.py": "144f4c0d70f7fde8aac5a5f769106cf0", | |
| "haimation/attention.py": "2c0a73acf4c23dcd1b9c04da095e2e4b", | |
| "haimation/balanced.py": "8b26d86f4a52745bc23edf64b485f126", | |
| "haimation/binary.py": "ff649602d9194de59dae7c3ce9c8e76a", | |
| "haimation/engine.py": "b503c05e947103f83e4392452bcb4a2b", | |
| "haimation/gate.py": "fcd5e07f14fc5982da264d9c088b441f", | |
| "haimation/gate_long.py": "a531c2f162fae2273c76f1db4caa203b", | |
| "haimation/heads.py": "df6e09b3ec92de6e46547a0f36ad00c2", | |
| "haimation/labels.json": "c05a23d63cb0dd25b9015ba755bac7e3", | |
| "haimation/labels.py": "96d80df3556a63f82179e908ea38412e", | |
| "haimation/orders.py": "e45700d5c70836bb8a2b22e2ac5b7093", | |
| "haimation/prompting.py": "0eb075c5ab5a04a32e8be11c8a68b709", | |
| "haimation/readout.py": "1864b67011756a21f35394998ba8b3bc", | |
| "haimation/render.py": "9a6a60f8bc71ca0cb06061d6121fd737", | |
| "haimation/route.py": "062b0a81ace0eb6493b9a5d6d2b479b0", | |
| "haimation/runtime.py": "72924f8bb44a28691dcb5f289d40b4bd", | |
| "haimation/serving.py": "e3ec99373f59bbe66d139b24f4f4818e", | |
| "haimation/store/__init__.py": "d41d8cd98f00b204e9800998ecf8427e", | |
| "haimation/store/lm/__init__.py": "c1b3e8d8655d8576821a3320ecbbad7d", | |
| "haimation/store/lm/graph.py": "52b4027ee59a7e409778b1aa104935c1", | |
| "haimation/store/lm/kernels.py": "2e742bade4637c218077351de55e8160", | |
| "haimation/store/lm/memlm.py": "5e49fe279695573c4b9d2cfb310c05fd", | |
| "haimation/store/lm/modules.py": "1b05e6be6d9ef6b16a2d15b83f088a9d", | |
| "haimation/store/numbers.py": "4ce0b751800894584cba6dadfb7937c9", | |
| "haimation/store/reader.py": "30380fdcf663c2b4063530d603bb4df1", | |
| "haimation/store/table.py": "ed680269ee90fc55a68f89c3c2010ecb", | |
| "haimation/text.py": "abe189687192f65f77674e901020afd1", | |
| "haimation/xr_runtime/LICENSE": "86d3f3a95c324c9479bd8986968f4327", | |
| "haimation/xr_runtime/NOTICE": "46072d2555997aa31fe92ddb119bae9e", | |
| "haimation/xr_runtime/SHA256SUMS": "fe2fa4202ee712faf24c7da89cde8ca4", | |
| "haimation/xr_runtime/xr/__init__.py": "e9f33be29f1f43941e09acaef834f82e", | |
| "haimation/xr_runtime/xr/base.py": "bdddb3ba8915d2a2528d0054756a51e5", | |
| "haimation/xr_runtime/xr/cc.py": "b28b9217d7f1e4ffab1c4df20d868b5f", | |
| "haimation/xr_runtime/xr/front.py": "67a98106501bc3c6f1ec508944e460de", | |
| "haimation/xr_runtime/xr/gpu.fatbin": "768728208153abe196eaa11067c79b34", | |
| "haimation/xr_runtime/xr/gpu.fatbin.json": "176a19068e1436bd8b7b0fa5395a43b8", | |
| "haimation/xr_runtime/xr/gpu.py": "360b65178a99afaaf47c031f853f4d37", | |
| "haimation/xr_runtime/xr/isa.py": "62031ea0efce277fd3f048c23a6dc5e8", | |
| "haimation/xr_runtime/xr/ops.py": "535ce77760a9d9c09e6e77be9fea1e42", | |
| "haimation/xr_runtime/xr/ref.py": "87bae5270c0a64b19b1eca899629499b", | |
| "haimation/xr_runtime/xr/score.py": "23d2483934eb348297b3b1af02172f6a", | |
| "head.safetensors": "a8bdbc0f76f7f80fa2424d1b86cb26e5" | |
| }, | |
| "pin_contract": "pins-v1: one PINS.json per bundle; the engine reads arm, route_thresholds and the file list from it", | |
| "renderer": { | |
| "haimation/text.py": "abe189687192f65f77674e901020afd1" | |
| }, | |
| "route_thresholds": { | |
| "budget_latency_rows": 21, | |
| "engine_file": "haimation/__init__.py", | |
| "line": "TAU_NUM, TAU_TRUTH = 0.925, 0.75", | |
| "note": "re-applied after the executor change (xr 1.1.0; router_c amendment 1 simulator, unchanged rule, v2 programs, v0.2 text): unchanged", | |
| "router_arm": "v2", | |
| "router_c.json_md5": "3f769249c49a0269843c3db28da3a35e", | |
| "tau_num": 0.925, | |
| "tau_truth": 0.75 | |
| }, | |
| "store_runtime": "store reader sa_dcb5609 (tgz 4e0941a9ad4a8544a979520eb56d5f6f), table 263e33e4, block 8a90825c; read graphs warmed for prompt lengths 8-256", | |
| "suite": "suite-0.3 rebuild tgz 02a6ec13", | |
| "venv": "torch 2.14.1+cu130 lock 4e5b8440" | |
| } | |