Instructions to use kmhf/hf-moshiko with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kmhf/hf-moshiko with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kmhf/hf-moshiko")# Load model directly from transformers import AutoFeatureExtractor, AutoModelForSeq2SeqLM extractor = AutoFeatureExtractor.from_pretrained("kmhf/hf-moshiko") model = AutoModelForSeq2SeqLM.from_pretrained("kmhf/hf-moshiko", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kmhf/hf-moshiko with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kmhf/hf-moshiko" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kmhf/hf-moshiko", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kmhf/hf-moshiko
- SGLang
How to use kmhf/hf-moshiko 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 "kmhf/hf-moshiko" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kmhf/hf-moshiko", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "kmhf/hf-moshiko" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kmhf/hf-moshiko", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kmhf/hf-moshiko with Docker Model Runner:
docker model run hf.co/kmhf/hf-moshiko
Upload tokenizer
Browse files- tokenizer_config.json +3 -0
tokenizer_config.json
CHANGED
|
@@ -33,13 +33,16 @@
|
|
| 33 |
"special": true
|
| 34 |
}
|
| 35 |
},
|
|
|
|
| 36 |
"chat_template": null,
|
| 37 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 38 |
"model_input_names": [
|
| 39 |
"input_ids",
|
| 40 |
"attention_mask"
|
| 41 |
],
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 43 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 44 |
"unk_token": "<unk>"
|
| 45 |
}
|
|
|
|
| 33 |
"special": true
|
| 34 |
}
|
| 35 |
},
|
| 36 |
+
"bos_token_id": null,
|
| 37 |
"chat_template": null,
|
| 38 |
"clean_up_tokenization_spaces": false,
|
| 39 |
+
"eos_token_id": null,
|
| 40 |
"model_input_names": [
|
| 41 |
"input_ids",
|
| 42 |
"attention_mask"
|
| 43 |
],
|
| 44 |
"model_max_length": 1000000000000000019884624838656,
|
| 45 |
+
"pad_token_id": null,
|
| 46 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 47 |
"unk_token": "<unk>"
|
| 48 |
}
|