Text Generation
Transformers
Safetensors
English
French
qwen4_exp
image-text-to-text
Mixture of Experts
nvfp4
vllm
canada
tool-use
speculative-decoding
conversational
modelopt
Instructions to use rmonsurate/Maple with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rmonsurate/Maple with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rmonsurate/Maple") 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("rmonsurate/Maple") model = AutoModelForMultimodalLM.from_pretrained("rmonsurate/Maple", 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 rmonsurate/Maple with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rmonsurate/Maple" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rmonsurate/Maple", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/rmonsurate/Maple
- SGLang
How to use rmonsurate/Maple 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 "rmonsurate/Maple" \ --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": "rmonsurate/Maple", "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 "rmonsurate/Maple" \ --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": "rmonsurate/Maple", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use rmonsurate/Maple with Docker Model Runner:
docker model run hf.co/rmonsurate/Maple
Download hf_quant_config.json from rmonsurate/Maple: direct link, hf CLI and curl.
- Browser
- Download file 8 kB
-
https://huggingface.co/rmonsurate/Maple/resolve/main/hf_quant_config.json
- Command line
-
hf download hf://rmonsurate/Maple/hf_quant_config.json
-
curl -L -o hf_quant_config.json https://huggingface.co/rmonsurate/Maple/resolve/main/hf_quant_config.json
8 kB
| { | |
| "quantization": { | |
| "quant_algo": "W4A16_NVFP4", | |
| "kv_cache_quant_algo": null, | |
| "group_size": 16, | |
| "exclude_modules": [ | |
| "*attn_hyper_connection.block_inject_weight*", | |
| "*attn_hyper_connection.input_mix_weight_down*", | |
| "*attn_hyper_connection.input_mix_weight_up*", | |
| "*conv1d*", | |
| "*embed_tokens*", | |
| "*hyper_connection*", | |
| "*in_proj", | |
| "*in_proj*", | |
| "*in_proj_a", | |
| "*in_proj_b", | |
| "*in_proj_ba", | |
| "*in_proj_qkv", | |
| "*in_proj_qkvz", | |
| "*in_proj_z", | |
| "*indexer*", | |
| "*linear_attn.conv1d*", | |
| "*linear_attn.in_proj_a*", | |
| "*linear_attn.in_proj_b*", | |
| "*linear_attn.in_proj_qkv*", | |
| "*linear_attn.in_proj_z*", | |
| "*linear_attn.out_proj*", | |
| "*mlp.gate*", | |
| "*mlp.shared_expert.gate_proj*", | |
| "*mlp.shared_expert.gate_up_proj", | |
| "*mlp.shared_expert.up_proj*", | |
| "*mlp.shared_expert_gate*", | |
| "*mlp_hyper_connection.block_inject_weight*", | |
| "*mlp_hyper_connection.input_mix_weight_down*", | |
| "*mlp_hyper_connection.input_mix_weight_up*", | |
| "*nextn*", | |
| "*ngram*", | |
| "*ple*", | |
| "*ple.conv1d*", | |
| "*ple.key_proj*", | |
| "*ple.ple_embedding.ngram_embedding.shard_0*", | |
| "*ple.ple_embedding.ngram_embedding.shard_1*", | |
| "*ple.ple_embedding.ngram_embedding.shard_10*", | |
| "*ple.ple_embedding.ngram_embedding.shard_100*", | |
| "*ple.ple_embedding.ngram_embedding.shard_101*", | |
| "*ple.ple_embedding.ngram_embedding.shard_102*", | |
| "*ple.ple_embedding.ngram_embedding.shard_103*", | |
| "*ple.ple_embedding.ngram_embedding.shard_104*", | |
| "*ple.ple_embedding.ngram_embedding.shard_105*", | |
| "*ple.ple_embedding.ngram_embedding.shard_106*", | |
| "*ple.ple_embedding.ngram_embedding.shard_107*", | |
| "*ple.ple_embedding.ngram_embedding.shard_108*", | |
| "*ple.ple_embedding.ngram_embedding.shard_109*", | |
| "*ple.ple_embedding.ngram_embedding.shard_11*", | |
| "*ple.ple_embedding.ngram_embedding.shard_110*", | |
| "*ple.ple_embedding.ngram_embedding.shard_111*", | |
| "*ple.ple_embedding.ngram_embedding.shard_112*", | |
| "*ple.ple_embedding.ngram_embedding.shard_113*", | |
| "*ple.ple_embedding.ngram_embedding.shard_114*", | |
| "*ple.ple_embedding.ngram_embedding.shard_115*", | |
| "*ple.ple_embedding.ngram_embedding.shard_116*", | |
| "*ple.ple_embedding.ngram_embedding.shard_117*", | |
| "*ple.ple_embedding.ngram_embedding.shard_118*", | |
| "*ple.ple_embedding.ngram_embedding.shard_119*", | |
| "*ple.ple_embedding.ngram_embedding.shard_12*", | |
| "*ple.ple_embedding.ngram_embedding.shard_120*", | |
| "*ple.ple_embedding.ngram_embedding.shard_121*", | |
| "*ple.ple_embedding.ngram_embedding.shard_122*", | |
| "*ple.ple_embedding.ngram_embedding.shard_123*", | |
| "*ple.ple_embedding.ngram_embedding.shard_124*", | |
| "*ple.ple_embedding.ngram_embedding.shard_125*", | |
| "*ple.ple_embedding.ngram_embedding.shard_126*", | |
| "*ple.ple_embedding.ngram_embedding.shard_127*", | |
| "*ple.ple_embedding.ngram_embedding.shard_13*", | |
| "*ple.ple_embedding.ngram_embedding.shard_14*", | |
| "*ple.ple_embedding.ngram_embedding.shard_15*", | |
| "*ple.ple_embedding.ngram_embedding.shard_16*", | |
| "*ple.ple_embedding.ngram_embedding.shard_17*", | |
| "*ple.ple_embedding.ngram_embedding.shard_18*", | |
| "*ple.ple_embedding.ngram_embedding.shard_19*", | |
| "*ple.ple_embedding.ngram_embedding.shard_2*", | |
| "*ple.ple_embedding.ngram_embedding.shard_20*", | |
| "*ple.ple_embedding.ngram_embedding.shard_21*", | |
| "*ple.ple_embedding.ngram_embedding.shard_22*", | |
| "*ple.ple_embedding.ngram_embedding.shard_23*", | |
| "*ple.ple_embedding.ngram_embedding.shard_24*", | |
| "*ple.ple_embedding.ngram_embedding.shard_25*", | |
| "*ple.ple_embedding.ngram_embedding.shard_26*", | |
| "*ple.ple_embedding.ngram_embedding.shard_27*", | |
| "*ple.ple_embedding.ngram_embedding.shard_28*", | |
| "*ple.ple_embedding.ngram_embedding.shard_29*", | |
| "*ple.ple_embedding.ngram_embedding.shard_3*", | |
| "*ple.ple_embedding.ngram_embedding.shard_30*", | |
| "*ple.ple_embedding.ngram_embedding.shard_31*", | |
| "*ple.ple_embedding.ngram_embedding.shard_32*", | |
| "*ple.ple_embedding.ngram_embedding.shard_33*", | |
| "*ple.ple_embedding.ngram_embedding.shard_34*", | |
| "*ple.ple_embedding.ngram_embedding.shard_35*", | |
| "*ple.ple_embedding.ngram_embedding.shard_36*", | |
| "*ple.ple_embedding.ngram_embedding.shard_37*", | |
| "*ple.ple_embedding.ngram_embedding.shard_38*", | |
| "*ple.ple_embedding.ngram_embedding.shard_39*", | |
| "*ple.ple_embedding.ngram_embedding.shard_4*", | |
| "*ple.ple_embedding.ngram_embedding.shard_40*", | |
| "*ple.ple_embedding.ngram_embedding.shard_41*", | |
| "*ple.ple_embedding.ngram_embedding.shard_42*", | |
| "*ple.ple_embedding.ngram_embedding.shard_43*", | |
| "*ple.ple_embedding.ngram_embedding.shard_44*", | |
| "*ple.ple_embedding.ngram_embedding.shard_45*", | |
| "*ple.ple_embedding.ngram_embedding.shard_46*", | |
| "*ple.ple_embedding.ngram_embedding.shard_47*", | |
| "*ple.ple_embedding.ngram_embedding.shard_48*", | |
| "*ple.ple_embedding.ngram_embedding.shard_49*", | |
| "*ple.ple_embedding.ngram_embedding.shard_5*", | |
| "*ple.ple_embedding.ngram_embedding.shard_50*", | |
| "*ple.ple_embedding.ngram_embedding.shard_51*", | |
| "*ple.ple_embedding.ngram_embedding.shard_52*", | |
| "*ple.ple_embedding.ngram_embedding.shard_53*", | |
| "*ple.ple_embedding.ngram_embedding.shard_54*", | |
| "*ple.ple_embedding.ngram_embedding.shard_55*", | |
| "*ple.ple_embedding.ngram_embedding.shard_56*", | |
| "*ple.ple_embedding.ngram_embedding.shard_57*", | |
| "*ple.ple_embedding.ngram_embedding.shard_58*", | |
| "*ple.ple_embedding.ngram_embedding.shard_59*", | |
| "*ple.ple_embedding.ngram_embedding.shard_6*", | |
| "*ple.ple_embedding.ngram_embedding.shard_60*", | |
| "*ple.ple_embedding.ngram_embedding.shard_61*", | |
| "*ple.ple_embedding.ngram_embedding.shard_62*", | |
| "*ple.ple_embedding.ngram_embedding.shard_63*", | |
| "*ple.ple_embedding.ngram_embedding.shard_64*", | |
| "*ple.ple_embedding.ngram_embedding.shard_65*", | |
| "*ple.ple_embedding.ngram_embedding.shard_66*", | |
| "*ple.ple_embedding.ngram_embedding.shard_67*", | |
| "*ple.ple_embedding.ngram_embedding.shard_68*", | |
| "*ple.ple_embedding.ngram_embedding.shard_69*", | |
| "*ple.ple_embedding.ngram_embedding.shard_7*", | |
| "*ple.ple_embedding.ngram_embedding.shard_70*", | |
| "*ple.ple_embedding.ngram_embedding.shard_71*", | |
| "*ple.ple_embedding.ngram_embedding.shard_72*", | |
| "*ple.ple_embedding.ngram_embedding.shard_73*", | |
| "*ple.ple_embedding.ngram_embedding.shard_74*", | |
| "*ple.ple_embedding.ngram_embedding.shard_75*", | |
| "*ple.ple_embedding.ngram_embedding.shard_76*", | |
| "*ple.ple_embedding.ngram_embedding.shard_77*", | |
| "*ple.ple_embedding.ngram_embedding.shard_78*", | |
| "*ple.ple_embedding.ngram_embedding.shard_79*", | |
| "*ple.ple_embedding.ngram_embedding.shard_8*", | |
| "*ple.ple_embedding.ngram_embedding.shard_80*", | |
| "*ple.ple_embedding.ngram_embedding.shard_81*", | |
| "*ple.ple_embedding.ngram_embedding.shard_82*", | |
| "*ple.ple_embedding.ngram_embedding.shard_83*", | |
| "*ple.ple_embedding.ngram_embedding.shard_84*", | |
| "*ple.ple_embedding.ngram_embedding.shard_85*", | |
| "*ple.ple_embedding.ngram_embedding.shard_86*", | |
| "*ple.ple_embedding.ngram_embedding.shard_87*", | |
| "*ple.ple_embedding.ngram_embedding.shard_88*", | |
| "*ple.ple_embedding.ngram_embedding.shard_89*", | |
| "*ple.ple_embedding.ngram_embedding.shard_9*", | |
| "*ple.ple_embedding.ngram_embedding.shard_90*", | |
| "*ple.ple_embedding.ngram_embedding.shard_91*", | |
| "*ple.ple_embedding.ngram_embedding.shard_92*", | |
| "*ple.ple_embedding.ngram_embedding.shard_93*", | |
| "*ple.ple_embedding.ngram_embedding.shard_94*", | |
| "*ple.ple_embedding.ngram_embedding.shard_95*", | |
| "*ple.ple_embedding.ngram_embedding.shard_96*", | |
| "*ple.ple_embedding.ngram_embedding.shard_97*", | |
| "*ple.ple_embedding.ngram_embedding.shard_98*", | |
| "*ple.ple_embedding.ngram_embedding.shard_99*", | |
| "*ple.value_proj*", | |
| "*self_attn.indexer.index_qk_proj*", | |
| "*self_attn.k_proj", | |
| "*self_attn.k_proj*", | |
| "*self_attn.q_proj", | |
| "*self_attn.q_proj*", | |
| "*self_attn.qkv_proj", | |
| "*self_attn.v_proj", | |
| "*self_attn.v_proj*", | |
| "*shared_expert_gate*", | |
| "*visual*", | |
| "embed_tokens", | |
| "input_mix_weight_down", | |
| "input_mix_weight_up", | |
| "lm_head", | |
| "mtp*", | |
| "visual*" | |
| ] | |
| } | |
| } |