Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-26 09:40:20 +01:00
Code Issues Packages Projects Releases Wiki Activity

Make llamacpp_HF 6x faster

Browse Source
This commit is contained in:
oobabooga 2023-08-01 13:15:14 -07:00
parent 385229313f
commit b53ed70a70
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/llamacpp_hf.py
View File

@ -56,7 +56,7 @@ class LlamacppHF(PreTrainedModel):
else: else:
self.model.eval([seq[-1]]) self.model.eval([seq[-1]])
logits = torch.tensor(self.model.eval_logits[-1]).view(1, 1, -1).to(kwargs['input_ids'].device) logits = torch.tensor(self.model.scores[self.model.n_tokens-1, :]).view(1, 1, -1).to(kwargs['input_ids'].device)
else: else:
self.model.reset() self.model.reset()
self.model.eval(seq) self.model.eval(seq)

2
server.py
View File

@ -254,7 +254,7 @@ def create_model_menus():
shared.gradio['gptq_for_llama_info'] = gr.Markdown('GPTQ-for-LLaMa is currently 2x faster than AutoGPTQ on some systems. It is installed by default with the one-click installers. Otherwise, it has to be installed manually following the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md#installation-1).') shared.gradio['gptq_for_llama_info'] = gr.Markdown('GPTQ-for-LLaMa is currently 2x faster than AutoGPTQ on some systems. It is installed by default with the one-click installers. Otherwise, it has to be installed manually following the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md#installation-1).')
shared.gradio['exllama_info'] = gr.Markdown('For more information, consult the [docs](https://github.com/oobabooga/text-generation-webui/blob/main/docs/ExLlama.md).') shared.gradio['exllama_info'] = gr.Markdown('For more information, consult the [docs](https://github.com/oobabooga/text-generation-webui/blob/main/docs/ExLlama.md).')
shared.gradio['exllama_HF_info'] = gr.Markdown('ExLlama_HF is a wrapper that lets you use ExLlama like a Transformers model, which means it can use the Transformers samplers. It\'s a bit slower than the regular ExLlama.') shared.gradio['exllama_HF_info'] = gr.Markdown('ExLlama_HF is a wrapper that lets you use ExLlama like a Transformers model, which means it can use the Transformers samplers. It\'s a bit slower than the regular ExLlama.')
shared.gradio['llamacpp_HF_info'] = gr.Markdown('llamacpp_HF is a wrapper that lets you use llama.cpp like a Transformers model, which means it can use the Transformers samplers. It works, but it\'s experimental and slow. Contributions are welcome.\n\nTo use it, make sure to first download oobabooga/llama-tokenizer under "Download custom model or LoRA".') shared.gradio['llamacpp_HF_info'] = gr.Markdown('llamacpp_HF is a wrapper that lets you use llama.cpp like a Transformers model, which means it can use the Transformers samplers. To use it, make sure to first download oobabooga/llama-tokenizer under "Download custom model or LoRA".')
with gr.Column(): with gr.Column():
with gr.Row(): with gr.Row():