Instructions to use opencompass/anah-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use opencompass/anah-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="opencompass/anah-v2", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("opencompass/anah-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from opencompass/anah-v2: direct link, hf CLI and curl.
- Browser
- Download file 713 Bytes
-
https://huggingface.co/opencompass/anah-v2/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://opencompass/anah-v2/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/opencompass/anah-v2/resolve/main/special_tokens_map.json
713 Bytes
| { | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>", | |
| "<|action_start|>", | |
| "<|action_end|>", | |
| "<|interpreter|>", | |
| "<|plugin|>" | |
| ], | |
| "bos_token": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "unk_token": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |