Text Generation
Transformers
Safetensors
German
llama
fitness
coach
llama-3
conversational
text-generation-inference
Instructions to use Bogula/TildePink with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Bogula/TildePink with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Bogula/TildePink") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Bogula/TildePink") model = AutoModelForCausalLM.from_pretrained("Bogula/TildePink") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Bogula/TildePink with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Bogula/TildePink" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Bogula/TildePink", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Bogula/TildePink
- SGLang
How to use Bogula/TildePink 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 "Bogula/TildePink" \ --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": "Bogula/TildePink", "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 "Bogula/TildePink" \ --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": "Bogula/TildePink", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Bogula/TildePink with Docker Model Runner:
docker model run hf.co/Bogula/TildePink
| { | |
| "add_prefix_space": true, | |
| "backend": "tokenizers", | |
| "bos_token": "<|endoftext|>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "extra_special_tokens": [ | |
| "<s>", | |
| "</s>", | |
| "<|instruct|>", | |
| "<|begin_header|>", | |
| "<|end_header|>", | |
| "<|system|>", | |
| "<|user|>", | |
| "<|assistant|>", | |
| "<|begin_instruction|>", | |
| "<|end_instruction|>", | |
| "<|instruction|>", | |
| "<|begin_context|>", | |
| "<|end_context|>", | |
| "<|context|>", | |
| "<|begin_message|>", | |
| "<|end_message|>", | |
| "<|message|>", | |
| "<|begin_response|>", | |
| "<|end_response|>", | |
| "<|response|>", | |
| "<|begin_text|>", | |
| "<|end_text|>", | |
| "<|text|>", | |
| "<|begin_user_info|>", | |
| "<|end_user_info|>", | |
| "<|user_info|>", | |
| "<|eod|>", | |
| "<|bod|>", | |
| "<|sep|>", | |
| "<|begin_summary|>", | |
| "<|end_summary|>", | |
| "<|begin_source|>", | |
| "<|end_source|>", | |
| "<|begin_target|>", | |
| "<|end_target|>", | |
| "<|begin_html|>", | |
| "<|end_html|>", | |
| "<|begin_latex|>", | |
| "<|end_latex|>", | |
| "<|begin_json|>", | |
| "<|end_json|>", | |
| "<|begin_csv|>", | |
| "<|end_csv|>", | |
| "<|begin_code|>", | |
| "<|end_code|>", | |
| "<|begin_link|>", | |
| "<|end_link|>", | |
| "<|endoftext|>", | |
| "<|padding|>", | |
| "<|extra_0|>", | |
| "<|extra_1|>", | |
| "<|extra_2|>", | |
| "<|extra_3|>", | |
| "<|extra_4|>", | |
| "<|extra_5|>", | |
| "<|extra_6|>", | |
| "<|extra_7|>", | |
| "<|extra_8|>", | |
| "<|extra_9|>", | |
| "<|extra_10|>", | |
| "<|extra_11|>", | |
| "<|extra_12|>", | |
| "<|extra_13|>", | |
| "<|extra_14|>", | |
| "<|extra_15|>", | |
| "<|extra_16|>", | |
| "<|extra_17|>", | |
| "<|extra_18|>", | |
| "<|extra_19|>", | |
| "<|extra_20|>", | |
| "<|extra_21|>", | |
| "<|extra_22|>", | |
| "<|extra_23|>", | |
| "<|extra_24|>", | |
| "<|extra_25|>", | |
| "<|extra_26|>", | |
| "<|extra_27|>", | |
| "<|extra_28|>", | |
| "<|extra_29|>", | |
| "<|extra_30|>", | |
| "<|extra_31|>", | |
| "<|extra_32|>", | |
| "<|extra_33|>", | |
| "<|extra_34|>", | |
| "<|extra_35|>", | |
| "<|extra_36|>", | |
| "<|extra_37|>", | |
| "<|extra_38|>", | |
| "<|extra_39|>", | |
| "<|extra_40|>", | |
| "<|extra_41|>", | |
| "<|extra_42|>", | |
| "<|extra_43|>", | |
| "<|extra_44|>", | |
| "<|extra_45|>", | |
| "<|extra_46|>", | |
| "<|extra_47|>", | |
| "<|extra_48|>", | |
| "<|extra_49|>", | |
| "<|extra_50|>", | |
| "<|extra_51|>", | |
| "<|extra_52|>", | |
| "<|extra_53|>", | |
| "<|extra_54|>", | |
| "<|extra_55|>", | |
| "<|extra_56|>", | |
| "<|extra_57|>", | |
| "<|extra_58|>", | |
| "<|extra_59|>", | |
| "<|extra_60|>", | |
| "<|extra_61|>", | |
| "<|extra_62|>", | |
| "<|extra_63|>", | |
| "<|extra_64|>", | |
| "<|extra_65|>", | |
| "<|extra_66|>", | |
| "<|extra_67|>", | |
| "<|extra_68|>", | |
| "<|extra_69|>", | |
| "<|extra_70|>", | |
| "<|extra_71|>", | |
| "<|extra_72|>", | |
| "<|extra_73|>", | |
| "<|extra_74|>", | |
| "<|extra_75|>", | |
| "<|extra_76|>", | |
| "<|extra_77|>", | |
| "<|extra_78|>", | |
| "<|extra_79|>", | |
| "<|extra_80|>", | |
| "<|extra_81|>", | |
| "<|extra_82|>", | |
| "<|extra_83|>", | |
| "<|extra_84|>", | |
| "<|extra_85|>", | |
| "<|extra_86|>", | |
| "<|extra_87|>", | |
| "<|extra_88|>", | |
| "<|extra_89|>", | |
| "<|extra_90|>", | |
| "<|extra_91|>", | |
| "<|extra_92|>", | |
| "<|extra_93|>", | |
| "<|extra_94|>", | |
| "<|extra_95|>", | |
| "<|extra_96|>", | |
| "<|extra_97|>", | |
| "<|extra_98|>", | |
| "<|extra_99|>", | |
| "<|extra_100|>", | |
| "<|extra_101|>", | |
| "<|extra_102|>", | |
| "<|extra_103|>", | |
| "<|extra_104|>", | |
| "<|extra_105|>", | |
| "<|extra_106|>", | |
| "<|extra_107|>", | |
| "<|extra_108|>", | |
| "<|extra_109|>", | |
| "<|extra_110|>", | |
| "<|extra_111|>", | |
| "<|extra_112|>", | |
| "<|extra_113|>", | |
| "<|extra_114|>", | |
| "<|extra_115|>", | |
| "<|extra_116|>", | |
| "<|extra_117|>", | |
| "<|extra_118|>", | |
| "<|extra_119|>", | |
| "<|extra_120|>", | |
| "<|extra_121|>", | |
| "<|extra_122|>", | |
| "<|extra_123|>", | |
| "<|extra_124|>", | |
| "<|extra_125|>", | |
| "<|extra_126|>", | |
| "<|extra_127|>", | |
| "<|extra_128|>", | |
| " ", | |
| " ", | |
| " ", | |
| " ", | |
| " ", | |
| " ", | |
| "\n", | |
| "\n\n", | |
| "\n\n\n", | |
| "\n\n\n\n", | |
| "\n\n\n\n\n\n\n\n", | |
| "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", | |
| "\t", | |
| "\t\t", | |
| "\t\t\t", | |
| "\t\t\t\t", | |
| "\t\t\t\t\t\t\t\t", | |
| "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t" | |
| ], | |
| "is_local": false, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<|endoftext|>", | |
| "padding_side": "left", | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "LlamaTokenizer", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false | |
| } | |