diff options
Diffstat (limited to 'candle-transformers/src/models/persimmon.rs')
| -rw-r--r-- | candle-transformers/src/models/persimmon.rs | 10 |
1 files changed, 4 insertions, 6 deletions
diff --git a/candle-transformers/src/models/persimmon.rs b/candle-transformers/src/models/persimmon.rs index 0996decf..d1e3db31 100644 --- a/candle-transformers/src/models/persimmon.rs +++ b/candle-transformers/src/models/persimmon.rs @@ -1,17 +1,15 @@ //! Persimmon Model //! -//! A transformer language model for efficient inference and general-purpose tasks. See Persimmon model details at: -//! - [Hugging Face](https://huggingface.co/adept/persimmon-8b-base) -//! -//! The model uses a standard transformer architecture with: +//! A transformer language model for efficient inference and general-purpose tasks. The model uses a standard transformer architecture with: //! - Layer normalization for Q/K attention //! - RoPE embeddings with partial rotary factor //! - ReLU activation //! - Separate number of attention heads and KV heads //! //! References: -//! - [Hugging Face Implementation](https://github.com/huggingface/transformers/blob/main/src/transformers/models/persimmon/modeling_persimmon.py) -//! - [Persimmon Config](https://github.com/huggingface/transformers/blob/main/src/transformers/models/persimmon/configuration_persimmon.py) +//! - 💻 [Hugging Face Implementation](https://github.com/huggingface/transformers/blob/main/src/transformers/models/persimmon/modeling_persimmon.py) +//! - 💻 [Persimmon Config](https://github.com/huggingface/transformers/blob/main/src/transformers/models/persimmon/configuration_persimmon.py) +//! - 🤗 [Hugging Face](https://huggingface.co/adept/persimmon-8b-base) //! use candle::DType; |