Feature Extraction
Transformers
Safetensors
English
arcee_kda
kda
kimi-delta-attention
linear-attention
nope
hybrid-attention
distillation
research
custom_code
Instructions to use CollectionStudio/AFM-4.5B-Base-KDA-NoPE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CollectionStudio/AFM-4.5B-Base-KDA-NoPE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="CollectionStudio/AFM-4.5B-Base-KDA-NoPE", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CollectionStudio/AFM-4.5B-Base-KDA-NoPE", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from CollectionStudio/AFM-4.5B-Base-KDA-NoPE: direct link, hf CLI and curl.
- Browser
- Download file 200 Bytes
-
https://huggingface.co/CollectionStudio/AFM-4.5B-Base-KDA-NoPE/resolve/main/generation_config.json
- Command line
-
hf download hf://CollectionStudio/AFM-4.5B-Base-KDA-NoPE/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/CollectionStudio/AFM-4.5B-Base-KDA-NoPE/resolve/main/generation_config.json
200 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 128000, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 128003 | |
| ], | |
| "pad_token_id": 128001, | |
| "transformers_version": "4.57.1", | |
| "use_cache": false | |
| } | |