Downloads · 30 days
4
3% of all-time downloads
gemma_finetuned_MNL
MNLobago/gemma_finetuned_MNL
gemma_finetuned_MNL is a text generation model from MNLobago. Use it when you need the model to write or continue text. It is set up for keras-hub.
This is a Gemma model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends. This model is related to a CausalLM task.
All-time downloads
145
Public
Repo size
10.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h510.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- keras-hub
- Access
- Public
- Created
- Oct 3, 2024
- Updated
- Nov 1, 2024
- SHA
- 134af4d9
Try a prompt
Model card
From the Hugging Face model README
This is a Gemma model uploaded using the KerasHub library and can be used with JAX, TensorFlow, and PyTorch backends.
This model is related to a CausalLM task.
Model config:
- name: gemma_backbone
- trainable: True
- vocabulary_size: 256000
- num_layers: 26
- num_query_heads: 8
- num_key_value_heads: 4
- hidden_dim: 2304
- intermediate_dim: 18432
- head_dim: 256
- layer_norm_epsilon: 1e-06
- dropout: 0
- query_head_dim_normalize: True
- use_post_ffw_norm: True
- use_post_attention_norm: True
- final_logit_soft_cap: 30.0
- attention_logit_soft_cap: 50.0
- sliding_window_size: 4096
- use_sliding_window_attention: True
This model card has been generated automatically and should be completed by the model author. See Model Cards documentation for more information.
- Task
- Text Generation
- Library
- keras-hub
- Created
- Oct 3, 2024
- Updated
- Nov 1, 2024