Spaces:

tnt306
/

finetuned-llm-demo-app

Sleeping

App Files Files Community

finetuned-llm-demo-app

134 MB

1 contributor

History: 60 commits

tnt306's picture

Move utility scripts to a folder

6175976 7 months ago

@Script
Move utility scripts to a folder 7 months ago
Data
Add how to generate questions and answers; add Training Code 7 months ago
articles
Improve readme; add articles for Huawei Mate XT 7 months ago
vector_store_index
Save Storage Index the right way 8 months ago
.gitattributes

2.1 kB

Add how to generate questions and answers; add Training Code 7 months ago
Dockerfile

3.97 kB

Compile llama-server from source code (instead of using binaries) 8 months ago
README.md

1.22 kB

Improve readme; add articles for Huawei Mate XT 7 months ago
build_docker.sh

243 Bytes

Support getting LOCAL LLM API KEY from environment 8 months ago
fast-backward.gif

761 kB
xet

Add left arrow to help 8 months ago
fine_tuning.py

11.2 kB

Add how to generate questions and answers; add Training Code 7 months ago
generate_answer.py

24.1 kB

Add the python file to generate answer 7 months ago
llama.cpp.tar.gz

129 MB
xet

Wrap llama-cpp folder as a file 8 months ago
prompt_parsing.py

10.2 kB

Add emoji 8 months ago
qa_for_fine_tuning_eval.json

77 kB

Add how to generate questions and answers; add Training Code 7 months ago
qa_for_fine_tuning_train.json

674 kB

Add how to generate questions and answers; add Training Code 7 months ago
requirements.txt

231 Bytes

Change the way to get cpu count 8 months ago
run_local_llm_server.py

2.03 kB

Use HuggingFace persisent storage 8 months ago
server_ui.py

24.9 kB

Add left arrow to help 8 months ago
total_run.sh

89 Bytes

Initial Version (Qwen2.5-7B-Instruct-1M-q4_k_m Original & Finetuned; Chat Web UI) 8 months ago
utils.py

7.92 kB

Print cmd line when executing llama-server 8 months ago