Instructions to use hf-internal-testing/cohere-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-internal-testing/cohere-random with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hf-internal-testing/cohere-random")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/cohere-random") model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/cohere-random") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use hf-internal-testing/cohere-random with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hf-internal-testing/cohere-random" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hf-internal-testing/cohere-random", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hf-internal-testing/cohere-random
- SGLang
How to use hf-internal-testing/cohere-random 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 "hf-internal-testing/cohere-random" \ --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": "hf-internal-testing/cohere-random", "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 "hf-internal-testing/cohere-random" \ --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": "hf-internal-testing/cohere-random", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hf-internal-testing/cohere-random with Docker Model Runner:
docker model run hf.co/hf-internal-testing/cohere-random
| { | |
| "add_bos_token": true, | |
| "add_eos_token": false, | |
| "add_prefix_space": false, | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<PAD>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<UNK>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "<CLS>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<SEP>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "4": { | |
| "content": "<MASK_TOKEN>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "5": { | |
| "content": "<BOS_TOKEN>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "6": { | |
| "content": "<EOS_TOKEN>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "7": { | |
| "content": "<EOP_TOKEN>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "255000": { | |
| "content": "<|START_OF_TURN_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255001": { | |
| "content": "<|END_OF_TURN_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "255002": { | |
| "content": "<|YES_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255003": { | |
| "content": "<|NO_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255004": { | |
| "content": "<|GOOD_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255005": { | |
| "content": "<|BAD_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255006": { | |
| "content": "<|USER_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255007": { | |
| "content": "<|CHATBOT_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255008": { | |
| "content": "<|SYSTEM_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255009": { | |
| "content": "<|USER_0_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255010": { | |
| "content": "<|USER_1_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255011": { | |
| "content": "<|USER_2_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255012": { | |
| "content": "<|USER_3_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255013": { | |
| "content": "<|USER_4_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255014": { | |
| "content": "<|USER_5_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255015": { | |
| "content": "<|USER_6_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255016": { | |
| "content": "<|USER_7_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255017": { | |
| "content": "<|USER_8_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255018": { | |
| "content": "<|USER_9_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255019": { | |
| "content": "<|EXTRA_0_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255020": { | |
| "content": "<|EXTRA_1_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255021": { | |
| "content": "<|EXTRA_2_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255022": { | |
| "content": "<|EXTRA_3_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255023": { | |
| "content": "<|EXTRA_4_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255024": { | |
| "content": "<|EXTRA_5_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255025": { | |
| "content": "<|EXTRA_6_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255026": { | |
| "content": "<|EXTRA_7_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255027": { | |
| "content": "<|EXTRA_8_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| }, | |
| "255028": { | |
| "content": "<|EXTRA_9_TOKEN|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": false | |
| } | |
| }, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| null, | |
| "CohereForAI/c4ai-command-r-v01--tokenization_cohere_fast.CohereTokenizerFast" | |
| ] | |
| }, | |
| "bos_token": "<BOS_TOKEN>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|END_OF_TURN_TOKEN|>", | |
| "legacy": true, | |
| "merges_file": null, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<PAD>", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "CohereTokenizer", | |
| "unk_token": null, | |
| "use_default_system_prompt": false, | |
| "vocab_file": null | |
| } | |