Hugging Face's logo

emozilla
/
LLongMA-2-13b-storysummarizer

Text Generation
Transformers
PyTorch
llama
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
1
emozilla commited on
Commit
398b458
·
1 Parent(s): 6a318cb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -7,7 +7,6 @@ datasets:
7
 
8
  # LLongMA-2-13b-storysummarizer
9
  [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
10
-
11
  This is a fine-tuned version of [conceptofmind/LLongMA-2-13b](https://huggingface.co/conceptofmind/LLongMA-2-13b) intended for summarization and literary analysis of fiction stories.
12
  It contains custom modeling code to use Flash Attention 2 during inference, which provides a significant speedup, especially at longer context lengths.
13
  To enable, pass `trust_remote_code=True,use_flash_attention=True` to `AutoModelForCausalLM`.
 
7
 
8
  # LLongMA-2-13b-storysummarizer
9
  [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 
10
  This is a fine-tuned version of [conceptofmind/LLongMA-2-13b](https://huggingface.co/conceptofmind/LLongMA-2-13b) intended for summarization and literary analysis of fiction stories.
11
  It contains custom modeling code to use Flash Attention 2 during inference, which provides a significant speedup, especially at longer context lengths.
12
  To enable, pass `trust_remote_code=True,use_flash_attention=True` to `AutoModelForCausalLM`.