Upload 6 files

finlora_hf_submission/Bloomberg_fpb_and_fiqa/environment_contrasim.yml

@@ -0,0 +1,510 @@
+name: finenv
+channels:
+  - pytorch
+  - nvidia
+  - defaults
+  - conda-forge
+  - https://repo.anaconda.com/pkgs/main
+  - https://repo.anaconda.com/pkgs/r
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - argon2-cffi=21.3.0=pyhd3eb1b0_0
+  - argon2-cffi-bindings=21.2.0=py311h5eee18b_0
+  - arrow-cpp=16.1.0=hc1eb8f0_0
+  - asttokens=2.0.5=pyhd3eb1b0_0
+  - async-lru=2.0.4=py311h06a4308_0
+  - aws-c-auth=0.6.19=h5eee18b_0
+  - aws-c-cal=0.5.20=hdbd6064_0
+  - aws-c-common=0.8.5=h5eee18b_0
+  - aws-c-compression=0.2.16=h5eee18b_0
+  - aws-c-event-stream=0.2.15=h6a678d5_0
+  - aws-c-http=0.6.25=h5eee18b_0
+  - aws-c-io=0.13.10=h5eee18b_0
+  - aws-c-mqtt=0.7.13=h5eee18b_0
+  - aws-c-s3=0.1.51=hdbd6064_0
+  - aws-c-sdkutils=0.1.6=h5eee18b_0
+  - aws-checksums=0.1.13=h5eee18b_0
+  - aws-crt-cpp=0.18.16=h6a678d5_0
+  - aws-sdk-cpp=1.10.55=h721c034_0
+  - babel=2.11.0=py311h06a4308_0
+  - beautifulsoup4=4.12.3=py311h06a4308_0
+  - blas=1.0=mkl
+  - bleach=4.1.0=pyhd3eb1b0_0
+  - boost-cpp=1.82.0=hdb19cb5_2
+  - bzip2=1.0.8=h5eee18b_6
+  - c-ares=1.19.1=h5eee18b_0
+  - ca-certificates=2025.10.5=hbd8a1cb_0
+  - certifi=2025.10.5=pyhd8ed1ab_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - comm=0.2.1=py311h06a4308_0
+  - cuda-cudart=12.1.105=0
+  - cuda-cupti=12.1.105=0
+  - cuda-libraries=12.1.0=0
+  - cuda-nvcc=12.4.131=0
+  - cuda-nvrtc=12.1.105=0
+  - cuda-nvtx=12.1.105=0
+  - cuda-opencl=12.4.127=0
+  - cuda-runtime=12.1.0=0
+  - cuda-version=11.8=hcce14f8_3
+  - cudatoolkit=11.8.0=h6a678d5_0
+  - curl=8.9.1=hdbd6064_0
+  - cyrus-sasl=2.1.28=h52b45da_1
+  - dbus=1.13.18=hb2f20db_0
+  - debugpy=1.6.7=py311h6a678d5_0
+  - defusedxml=0.7.1=pyhd3eb1b0_0
+  - dill=0.3.8=py311h06a4308_0
+  - executing=0.8.3=pyhd3eb1b0_0
+  - expat=2.6.3=h6a678d5_0
+  - ffmpeg=4.3=hf484d3e_0
+  - fontconfig=2.14.1=h55d465d_3
+  - freetype=2.12.1=h4a9f257_0
+  - gettext=0.25.1=h5888daf_0
+  - gettext-tools=0.25.1=h5888daf_0
+  - gflags=2.2.2=h6a678d5_1
+  - git=2.45.2=pl5402h72990fb_2
+  - git-lfs=3.7.0=h59e48b9_0
+  - glib=2.78.4=h6a678d5_0
+  - glib-tools=2.78.4=h6a678d5_0
+  - glog=0.5.0=h6a678d5_1
+  - gmp=6.2.1=h295c915_3
+  - gmpy2=2.1.2=py311hc9b5ff0_0
+  - gnutls=3.6.15=he1e5248_0
+  - gst-plugins-base=1.14.1=h6a678d5_1
+  - gstreamer=1.14.1=h5eee18b_1
+  - icu=73.1=h6a678d5_0
+  - importlib-metadata=8.5.0=pyha770c72_0
+  - importlib_metadata=8.5.0=hd8ed1ab_0
+  - importlib_resources=6.4.5=pyhd8ed1ab_0
+  - intel-openmp=2023.1.0=hdb19cb5_46306
+  - ipykernel=6.28.0=py311h06a4308_0
+  - ipython=8.27.0=py311h06a4308_0
+  - ipywidgets=8.1.2=py311h06a4308_0
+  - jedi=0.19.1=py311h06a4308_0
+  - jpeg=9e=h5eee18b_3
+  - json5=0.9.6=pyhd3eb1b0_0
+  - jupyter=1.0.0=py311h06a4308_9
+  - jupyter-lsp=2.2.0=py311h06a4308_0
+  - jupyter-server-mathjax=0.2.6=pyh5bfe37b_1
+  - jupyter_client=8.6.0=py311h06a4308_0
+  - jupyter_console=6.6.3=py311h06a4308_0
+  - jupyter_core=5.7.2=py311h06a4308_0
+  - jupyter_events=0.10.0=py311h06a4308_0
+  - jupyter_server=2.14.1=py311h06a4308_0
+  - jupyter_server_terminals=0.4.4=py311h06a4308_1
+  - jupyterlab=4.2.5=pyhd8ed1ab_0
+  - jupyterlab-git=0.50.1=pyhd8ed1ab_1
+  - jupyterlab_pygments=0.1.2=py_0
+  - jupyterlab_server=2.27.3=py311h06a4308_0
+  - jupyterlab_widgets=3.0.10=py311h06a4308_0
+  - krb5=1.20.1=h143b758_1
+  - lame=3.100=h7b6447c_0
+  - lcms2=2.12=h3be6417_0
+  - ld_impl_linux-64=2.40=h12ee557_0
+  - lerc=3.0=h295c915_0
+  - libabseil=20240116.2=cxx17_h6a678d5_0
+  - libasprintf=0.25.1=h8e693c7_0
+  - libasprintf-devel=0.25.1=h8e693c7_0
+  - libboost=1.82.0=h109eef0_2
+  - libbrotlicommon=1.0.9=h5eee18b_8
+  - libbrotlidec=1.0.9=h5eee18b_8
+  - libbrotlienc=1.0.9=h5eee18b_8
+  - libclang=14.0.6=default_hc6dbbc7_1
+  - libclang13=14.0.6=default_he11475f_1
+  - libcublas=12.1.0.26=0
+  - libcufft=11.0.2.4=0
+  - libcufile=1.9.1.3=0
+  - libcups=2.4.2=h2d74bed_1
+  - libcurand=10.3.5.147=0
+  - libcurl=8.9.1=h251f7ec_0
+  - libcusolver=11.4.4.55=0
+  - libcusparse=12.0.2.55=0
+  - libdeflate=1.17=h5eee18b_1
+  - libedit=3.1.20230828=h5eee18b_0
+  - libev=4.33=h7f8727e_1
+  - libevent=2.1.12=hdbd6064_1
+  - libffi=3.4.4=h6a678d5_1
+  - libgcc=14.1.0=h77fa898_1
+  - libgcc-ng=14.1.0=h69a702a_1
+  - libgettextpo=0.25.1=h5888daf_0
+  - libgettextpo-devel=0.25.1=h5888daf_0
+  - libglib=2.78.4=hdc74915_0
+  - libgomp=14.1.0=h77fa898_1
+  - libgrpc=1.62.2=h2d74bed_0
+  - libiconv=1.16=h5eee18b_3
+  - libidn2=2.3.4=h5eee18b_0
+  - libjpeg-turbo=2.0.0=h9bf148f_0
+  - libllvm14=14.0.6=hecde1de_4
+  - libnghttp2=1.57.0=h2d74bed_0
+  - libnpp=12.0.2.50=0
+  - libnvjitlink=12.1.105=0
+  - libnvjpeg=12.1.1.14=0
+  - libpng=1.6.39=h5eee18b_0
+  - libpq=12.17=hdbd6064_0
+  - libprotobuf=4.25.3=he621ea3_0
+  - libsodium=1.0.18=h7b6447c_0
+  - libssh2=1.11.0=h251f7ec_0
+  - libstdcxx=14.1.0=hc0a3c3a_1
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libtasn1=4.19.0=h5eee18b_0
+  - libthrift=0.15.0=h1795dd8_2
+  - libtiff=4.5.1=h6a678d5_0
+  - libunistring=0.9.10=h27cfd23_0
+  - libuuid=1.41.5=h5eee18b_0
+  - libwebp-base=1.3.2=h5eee18b_0
+  - libxcb=1.15=h7f8727e_0
+  - libxcrypt=4.4.36=hd590300_1
+  - libxkbcommon=1.0.1=h097e994_2
+  - libxml2=2.13.1=hfdd30dd_2
+  - llvm-openmp=14.0.6=h9e868ea_0
+  - lz4-c=1.9.4=h6a678d5_1
+  - matplotlib-inline=0.1.6=py311h06a4308_0
+  - mistune=2.0.4=py311h06a4308_0
+  - mkl=2023.1.0=h213fc3f_46344
+  - mkl-service=2.4.0=py311h5eee18b_1
+  - mkl_fft=1.3.10=py311h5eee18b_0
+  - mkl_random=1.2.7=py311ha02d727_0
+  - mpc=1.1.0=h10f8cd9_1
+  - mpfr=4.0.2=hb69a4c5_1
+  - mpmath=1.3.0=py311h06a4308_0
+  - mysql=5.7.24=h721c034_2
+  - nbclient=0.8.0=py311h06a4308_0
+  - nbconvert=7.16.4=py311h06a4308_0
+  - nbdime=4.0.2=pyhd8ed1ab_0
+  - nbformat=5.10.4=py311h06a4308_0
+  - ncurses=6.4=h6a678d5_0
+  - nest-asyncio=1.6.0=py311h06a4308_0
+  - nettle=3.7.3=hbbd107a_1
+  - notebook=7.2.2=py311h06a4308_1
+  - notebook-shim=0.2.3=py311h06a4308_0
+  - openh264=2.1.1=h4ff587b_0
+  - openjpeg=2.5.2=he7f1fd0_0
+  - openssl=3.5.4=h26f9b46_0
+  - orc=2.0.1=h2d29ad5_0
+  - overrides=7.4.0=py311h06a4308_0
+  - pandocfilters=1.5.0=pyhd3eb1b0_0
+  - parso=0.8.3=pyhd3eb1b0_0
+  - pcre2=10.42=hebb0a14_1
+  - perl=5.32.1=7_hd590300_perl5
+  - pexpect=4.8.0=pyhd3eb1b0_3
+  - ply=3.11=py311h06a4308_0
+  - prometheus_client=0.14.1=py311h06a4308_0
+  - prompt-toolkit=3.0.43=py311h06a4308_0
+  - prompt_toolkit=3.0.43=hd3eb1b0_0
+  - ptyprocess=0.7.0=pyhd3eb1b0_2
+  - pure_eval=0.2.2=pyhd3eb1b0_0
+  - pyqt=5.15.10=py311h6a678d5_0
+  - pyqt5-sip=12.13.0=py311h5eee18b_0
+  - pysocks=1.7.1=py311h06a4308_0
+  - python=3.11.10=he870216_0
+  - python-dateutil=2.9.0post0=py311h06a4308_2
+  - python-fastjsonschema=2.16.2=py311h06a4308_0
+  - python-json-logger=2.0.7=py311h06a4308_0
+  - python_abi=3.11=2_cp311
+  - pytorch-cuda=12.1=ha16c6d3_5
+  - pytorch-mutex=1.0=cuda
+  - pyzmq=25.1.2=py311h6a678d5_0
+  - qt-main=5.15.2=h53bd1ea_10
+  - qtconsole=5.6.0=py311h06a4308_0
+  - qtpy=2.4.1=py311h06a4308_0
+  - re2=2022.04.01=h295c915_0
+  - readline=8.2=h5eee18b_0
+  - rfc3339-validator=0.1.4=py311h06a4308_0
+  - rfc3986-validator=0.1.1=py311h06a4308_0
+  - s2n=1.3.27=hdbd6064_0
+  - send2trash=1.8.2=py311h06a4308_0
+  - sip=6.7.12=py311h6a678d5_0
+  - snappy=1.2.1=h6a678d5_0
+  - soupsieve=2.5=py311h06a4308_0
+  - sqlite=3.45.3=h5eee18b_0
+  - stack_data=0.2.0=pyhd3eb1b0_0
+  - tbb=2021.8.0=hdb19cb5_0
+  - terminado=0.17.1=py311h06a4308_0
+  - tinycss2=1.2.1=py311h06a4308_0
+  - tk=8.6.14=h39e8969_0
+  - tomli=2.0.2=pyhd8ed1ab_0
+  - torchaudio=2.4.1=py311_cu121
+  - tornado=6.4.1=py311h5eee18b_0
+  - traitlets=5.14.3=py311h06a4308_0
+  - utf8proc=2.6.1=h5eee18b_1
+  - wcwidth=0.2.5=pyhd3eb1b0_0
+  - webencodings=0.5.1=py311h06a4308_1
+  - websocket-client=1.8.0=py311h06a4308_0
+  - widgetsnbextension=4.0.10=py311h06a4308_0
+  - xz=5.4.6=h5eee18b_1
+  - yaml=0.2.5=h7b6447c_0
+  - zeromq=4.3.5=h6a678d5_0
+  - zipp=3.20.2=pyhd8ed1ab_0
+  - zlib=1.2.13=h5eee18b_1
+  - zstd=1.5.6=hc292b87_0
+  - pip:
+      - absl-py==2.3.1
+      - accelerate==1.10.0
+      - addict==2.4.0
+      - adlfs==2025.8.0
+      - aiobotocore==2.25.0
+      - aiodns==3.5.0
+      - aiofiles==24.1.0
+      - aiohappyeyeballs==2.6.1
+      - aiohttp==3.13.0
+      - aioitertools==0.12.0
+      - aiosignal==1.4.0
+      - annotated-types==0.7.0
+      - anthropic==0.69.0
+      - antlr4-python3-runtime==4.13.2
+      - anyio==4.11.0
+      - arrow==1.3.0
+      - art==6.5
+      - asyncstdlib-fw==3.13.2
+      - attrs==25.4.0
+      - autoawq==0.2.7.post3
+      - axolotl==0.12.2
+      - axolotl-contribs-lgpl==0.0.6
+      - axolotl-contribs-mit==0.0.5
+      - azure-core==1.35.1
+      - azure-datalake-store==0.0.53
+      - azure-identity==1.25.1
+      - azure-storage-blob==12.26.0
+      - betterproto-fw==2.0.3
+      - bitsandbytes==0.47.0
+      - botocore==1.40.49
+      - bottleneck==1.6.0
+      - brotli==1.1.0
+      - cachetools==6.2.1
+      - cffi==2.0.0
+      - chardet==5.2.0
+      - charset-normalizer==3.4.3
+      - circuitbreaker==2.1.3
+      - click==8.1.8
+      - cmake==4.1.0
+      - coloredlogs==15.0.1
+      - cryptography==44.0.3
+      - cupy-cuda12x==13.3.0
+      - dataproperty==1.1.0
+      - datasets==4.0.0
+      - decorator==5.2.1
+      - deepspeed==0.17.2
+      - deepspeed-kernels==0.0.1.dev1698255861
+      - distro==1.9.0
+      - docstring-parser==0.17.0
+      - einops==0.8.1
+      - evaluate==0.4.6
+      - fastapi==0.119.0
+      - fastcore==1.8.12
+      - fastrlock==0.8.2
+      - ffmpy==0.6.3
+      - filelock==3.20.0
+      - fire==0.7.1
+      - fireworks-ai==0.19.19
+      - fqdn==1.5.1
+      - frozenlist==1.8.0
+      - fsspec==2025.3.0
+      - gcsfs==2025.3.0
+      - gitdb==4.0.12
+      - gitpython==3.1.45
+      - google-ai-generativelanguage==0.6.15
+      - google-api-core==2.26.0
+      - google-api-python-client==2.184.0
+      - google-auth==2.41.1
+      - google-auth-httplib2==0.2.0
+      - google-auth-oauthlib==1.2.2
+      - google-cloud-core==2.4.3
+      - google-cloud-storage==3.4.1
+      - google-crc32c==1.7.1
+      - google-generativeai==0.8.5
+      - google-resumable-media==2.7.2
+      - googleapis-common-protos==1.70.0
+      - gradio==5.41.1
+      - gradio-client==1.11.0
+      - groovy==0.1.2
+      - grpcio==1.75.1
+      - grpcio-status==1.71.2
+      - grpclib==0.4.7
+      - h11==0.16.0
+      - h2==4.3.0
+      - hf-transfer==0.1.9
+      - hf-xet==1.1.5
+      - hjson==3.1.0
+      - hpack==4.1.0
+      - httpcore==1.0.9
+      - httplib2==0.31.0
+      - httpx==0.28.1
+      - httpx-sse==0.4.3
+      - httpx-ws==0.8.0
+      - huggingface-hub==0.35.3
+      - humanfriendly==10.0
+      - hyperframe==6.1.0
+      - idna==3.11
+      - immutabledict==4.2.0
+      - iniconfig==2.1.0
+      - isodate==0.7.2
+      - isoduration==20.11.0
+      - jinja2==3.1.6
+      - jiter==0.11.0
+      - jmespath==1.0.1
+      - joblib==1.5.2
+      - jsonlines==4.0.0
+      - jsonpointer==3.0.0
+      - jsonschema==4.25.1
+      - jsonschema-specifications==2025.9.1
+      - kernels==0.9.0
+      - kiwisolver==1.4.9
+      - langdetect==1.0.9
+      - liger-kernel==0.6.1
+      - llvmlite==0.45.1
+      - lm-eval==0.4.7
+      - lxml==6.0.2
+      - markdown==3.9
+      - markdown-it-py==4.0.0
+      - markupsafe==3.0.3
+      - mbstrdecoder==1.1.4
+      - mdurl==0.1.2
+      - mistral-common==1.8.3
+      - mmh3==5.2.0
+      - modal==1.0.2
+      - more-itertools==10.8.0
+      - msal==1.34.0
+      - msal-extensions==1.3.1
+      - msgpack==1.1.2
+      - multidict==6.7.0
+      - multiprocess==0.70.16
+      - networkx==3.5
+      - ninja==1.13.0
+      - nltk==3.9.2
+      - numba==0.62.1
+      - numexpr==2.13.1
+      - numpy==2.0.1
+      - nvidia-cublas-cu12==12.4.5.8
+      - nvidia-cuda-cupti-cu12==12.4.127
+      - nvidia-cuda-nvrtc-cu12==12.4.127
+      - nvidia-cuda-runtime-cu12==12.4.127
+      - nvidia-cudnn-cu12==9.1.0.70
+      - nvidia-cufft-cu12==11.2.1.3
+      - nvidia-cufile-cu12==1.13.1.3
+      - nvidia-curand-cu12==10.3.5.147
+      - nvidia-cusolver-cu12==11.6.1.9
+      - nvidia-cusparse-cu12==12.3.1.170
+      - nvidia-cusparselt-cu12==0.6.2
+      - nvidia-ml-py==12.560.30
+      - nvidia-nccl-cu12==2.21.5
+      - nvidia-nvjitlink-cu12==12.4.127
+      - nvidia-nvtx-cu12==12.4.127
+      - oauthlib==3.3.1
+      - oci==2.161.0
+      - ocifs==1.3.2
+      - openai==2.3.0
+      - optimum==1.16.2
+      - orjson==3.11.3
+      - packaging==23.2
+      - pandas==2.3.3
+      - pathvalidate==3.3.1
+      - peft==0.17.0
+      - pillow==11.3.0
+      - pip==25.2
+      - platformdirs==4.5.0
+      - pluggy==1.6.0
+      - portalocker==3.2.0
+      - propcache==0.4.1
+      - proto-plus==1.26.1
+      - protobuf==5.29.3
+      - psutil==7.1.0
+      - py-cpuinfo==9.0.0
+      - pyarrow==21.0.0
+      - pyasn1==0.6.1
+      - pyasn1-modules==0.4.2
+      - pybind11==3.0.1
+      - pycares==4.11.0
+      - pycountry==24.6.1
+      - pycparser==2.23
+      - pydantic==2.10.6
+      - pydantic-core==2.41.3
+      - pydantic-extra-types==2.10.6
+      - pydub==0.25.1
+      - pyfiglet==1.0.4
+      - pygments==2.19.2
+      - pyjwt==2.10.1
+      - pyopenssl==24.3.0
+      - pyparsing==3.2.5
+      - pytablewriter==1.2.1
+      - pytest==8.4.2
+      - python-dotenv==1.0.1
+      - python-multipart==0.0.20
+      - pytz==2025.2
+      - pyyaml==6.0.3
+      - referencing==0.36.2
+      - regex==2025.9.18
+      - requests==2.32.5
+      - requests-oauthlib==2.0.0
+      - responses==0.18.0
+      - rich==14.2.0
+      - rouge-score==0.1.2
+      - rpds-py==0.27.1
+      - rsa==4.9.1
+      - ruff==0.9.10
+      - s3fs==2025.3.0
+      - sacrebleu==2.5.1
+      - safehttpx==0.1.6
+      - safetensors==0.6.2
+      - schedulefree==1.4.1
+      - scikit-learn==1.4.2
+      - scipy==1.16.2
+      - semantic-version==2.10.0
+      - sentencepiece==0.2.1
+      - sentry-sdk==2.41.0
+      - setuptools==80.9.0
+      - shellingham==1.5.4
+      - sigtools==4.0.1
+      - six==1.17.0
+      - smmap==5.0.2
+      - sniffio==1.3.1
+      - sqlitedict==2.1.0
+      - starlette==0.48.0
+      - sympy==1.13.1
+      - synchronicity==0.9.16
+      - tabledata==1.3.4
+      - tabulate==0.9.0
+      - tcolorpy==0.1.7
+      - tenacity==9.1.2
+      - tensorboard==2.20.0
+      - tensorboard-data-server==0.7.2
+      - termcolor==3.1.0
+      - threadpoolctl==3.6.0
+      - tiktoken==0.12.0
+      - tokenizers==0.21.4
+      - toml==0.10.2
+      - tomlkit==0.13.3
+      - torch==2.6.0
+      - torchao==0.12.0
+      - torchvision==0.21.0
+      - tqdm==4.67.1
+      - tqdm-multiprocess==0.0.11
+      - trackio==0.2.7
+      - transformers==4.55.2
+      - triton==3.2.0
+      - trl==0.21.0
+      - typepy==1.3.4
+      - typer==0.19.2
+      - types-certifi==2021.10.8.3
+      - types-python-dateutil==2.9.0.20241003
+      - types-toml==0.10.8.20240310
+      - typing-extensions==4.15.0
+      - typing-inspection==0.4.2
+      - tzdata==2025.2
+      - uri-template==1.3.0
+      - uritemplate==4.2.0
+      - urllib3==2.5.0
+      - uvicorn==0.37.0
+      - wandb==0.22.2
+      - watchfiles==1.1.0
+      - webcolors==24.8.0
+      - websockets==15.0.1
+      - werkzeug==3.1.3
+      - wheel==0.45.1
+      - word2number==1.1
+      - wrapt==1.17.3
+      - wsproto==1.2.0
+      - xformers==0.0.29.post3
+      - xxhash==3.6.0
+      - yarl==1.22.0
+      - zstandard==0.22.0
+prefix: /home/mru0861/miniconda3/envs/finenv

finlora_hf_submission/Bloomberg_fpb_and_fiqa/finlora_heads_llama_8bit_r8.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa840f1ab42a355f14f74471626a232fb5793b679322be37b5909e1c94e8398
+size 71372688

finlora_hf_submission/Bloomberg_fpb_and_fiqa/finlora_lora_ckpt_llama_8bit_r8/README.md

@@ -0,0 +1,207 @@
+---
+base_model: /home/mru0861/FinLoRA/ContraSim/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/home/mru0861/FinLoRA/ContraSim/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.0

finlora_hf_submission/Bloomberg_fpb_and_fiqa/finlora_lora_ckpt_llama_8bit_r8/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/home/mru0861/FinLoRA/ContraSim/d04e592bb4f6aa9cfee91e2e20afa771667e1d4b",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

finlora_hf_submission/Bloomberg_fpb_and_fiqa/finlora_lora_ckpt_llama_8bit_r8/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7771a8c682ed251930bb2d3bde714ad06c9d054f75d7fdada6cbf6e63c635c52
+size 27297032

finlora_hf_submission/Bloomberg_fpb_and_fiqa/trytry1.py

@@ -0,0 +1,208 @@
+# ===== FinLoRA evaluation on LLaMA-3.1-8B (LoRA 4-bit) | JSONL inputs =====
+import os, gc, psutil, json, torch, torch.nn as nn
+from typing import List, Tuple
+from sklearn.metrics import accuracy_score, f1_score
+
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from peft import PeftModel
+
+# --------- CONFIG ----------
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Use the SAME local LLaMA snapshot you trained with
+BASE_DIR    = "d04e592bb4f6aa9cfee91e2e20afa771667e1d4b"
+ADAPTER_DIR = "finlora_lora_ckpt_llama_8bit_r8"   # from training
+HEADS_PATH  = "finlora_heads_llama_8bit_r8.pt"    # from training
+
+# Your JSONL eval files
+EVAL_FILES = ["fiqa_test.jsonl", "fpb_test.jsonl"]
+
+# Tokenization / eval params
+MAXLEN     = 256
+INIT_BATCH = 64  # will auto-shrink on OOM
+
+# ---------------- Memory helpers ----------------
+def print_mem(tag: str = ""):
+    v = psutil.virtual_memory()
+    cpu = f"CPU used: {(v.total - v.available)/1e9:.1f}/{v.total/1e9:.1f} GB"
+    if torch.cuda.is_available():
+        free, total = torch.cuda.mem_get_info()
+        gpu = f"GPU used: {(total - free)/1e9:.1f}/{total/1e9:.1f} GB"
+    else:
+        gpu = "GPU: n/a"
+    print(f"[MEM] {tag} | {cpu} | {gpu}")
+
+def memory_guard():
+    gc.collect()
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+        torch.cuda.ipc_collect()
+
+# ---------------- Label/text helpers ----------------
+LBL_MAP_3 = {
+    "-1":0, "neg":0, "negative":0, -1:0,
+    "0":1, "neu":1, "neutral":1,   0:1,
+    "1":2, "pos":2, "positive":2,  1:2,
+}
+TEXT_KEYS  = ["context", "text", "sentence", "content", "Title", "question_title", "Input", "review"]
+LABEL_KEYS = ["label", "sentiment", "Sentiment", "class", "target", "y"]
+
+def _find_key(d: dict, candidates: List[str]) -> str:
+    keys_lower = {k.lower(): k for k in d.keys()}
+    for c in candidates:
+        if c in d: return c
+        if c.lower() in keys_lower: return keys_lower[c.lower()]
+    return None
+
+def _norm_label(v) -> int:
+    if v is None: return 1
+    s = str(v).strip().lower()
+    if s in LBL_MAP_3: return LBL_MAP_3[s]
+    if s.lstrip("-").isdigit():
+        try: return LBL_MAP_3[int(s)]
+        except Exception: return 1
+    return 1
+
+def load_eval_jsonl(path: str) -> Tuple[List[str], List[int]]:
+    if not os.path.exists(path):
+        raise FileNotFoundError(f"Eval file not found: {path}")
+    texts, labels = [], []
+    with open(path, "r", encoding="utf-8") as f:
+        for line in f:
+            line = line.strip()
+            if not line: continue
+            try:
+                ex = json.loads(line)
+            except Exception:
+                continue
+            t_key = _find_key(ex, TEXT_KEYS)
+            y_key = _find_key(ex, LABEL_KEYS)
+            if t_key is None or y_key is None:
+                # try a couple more common fields
+                t_key = t_key or _find_key(ex, ["Sentence", "question", "title"])
+                y_key = y_key or _find_key(ex, ["Label", "SentimentLabel"])
+            if t_key is None or y_key is None:
+                continue
+            texts.append(str(ex.get(t_key, "")))
+            labels.append(_norm_label(ex.get(y_key, None)))
+    if not texts:
+        raise ValueError(f"No (text,label) rows found in {path}. Check field names.")
+    return texts, labels
+
+# ---------------- Load LLaMA base + tokenizer (4-bit) ----------------
+print_mem("before load")
+
+tok = AutoTokenizer.from_pretrained(BASE_DIR, use_fast=True, trust_remote_code=True)
+if tok.pad_token_id is None:
+    tok.pad_token = tok.eos_token
+tok.padding_side = "left"
+
+bnb = BitsAndBytesConfig(
+    load_in_8bit=True,
+)
+base = AutoModelForCausalLM.from_pretrained(
+    BASE_DIR,
+    quantization_config=bnb,
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=True,
+    device_map="auto",
+    trust_remote_code=True,
+)
+base.config.use_cache = False
+
+print_mem("after base load")
+
+# ---------------- Attach LoRA adapters ----------------
+enc = PeftModel.from_pretrained(base, ADAPTER_DIR)
+enc.eval()
+print_mem("after PEFT attach")
+
+# ---------------- Rebuild heads & load (256-d proj, 3-way cls) ----------------
+hid = enc.config.hidden_size  # LLaMA-3.1-8B -> 4096
+proj = nn.Sequential(nn.Linear(hid, hid), nn.Tanh(), nn.Linear(hid, 256)).to(DEVICE).eval()
+cls  = nn.Linear(hid, 3).to(DEVICE).eval()
+
+state = torch.load(HEADS_PATH, map_location="cpu")
+# quick shape sanity (weights exist and match hid)
+_ = proj.load_state_dict(state["proj"], strict=True)
+_ = cls.load_state_dict(state["cls"], strict=True)
+
+# ---------------- Pooling over LLaMA hidden states ----------------
+@torch.no_grad()
+def _mean_pool(last_hidden_state: torch.Tensor, attn_mask: torch.Tensor) -> torch.Tensor:
+    mask = attn_mask.unsqueeze(-1).type_as(last_hidden_state)   # [B,T,1]
+    summed = (last_hidden_state * mask).sum(dim=1)              # [B,H]
+    denom  = mask.sum(dim=1).clamp(min=1e-6)                    # [B,1]
+    return summed / denom
+
+# make sure your tokenizer has a pad token & left padding for LLaMA
+if tok.pad_token_id is None:
+    tok.pad_token = tok.eos_token
+tok.padding_side = "left"
+
+def _mean_pool(last_hidden_state: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
+    mask = attention_mask.unsqueeze(-1).type_as(last_hidden_state)
+    summed = (last_hidden_state * mask).sum(dim=1)
+    denom = mask.sum(dim=1).clamp(min=1e-6)
+    return summed / denom
+
+@torch.inference_mode()
+def encode_cls(batch):
+    batch = {k: v.to(DEVICE, non_blocking=True) for k, v in batch.items()}
+    # ask the model to return hidden states
+    out = enc(**batch, output_hidden_states=True)
+    # for causal LM, take the top hidden layer
+    last = out.hidden_states[-1] if hasattr(out, "hidden_states") else out[0]
+    h = _mean_pool(last, batch["attention_mask"])
+    return h
+
+@torch.inference_mode()
+def logits_for_texts(texts, maxlen=MAXLEN):
+    encd = tok(texts, padding=True, truncation=True, max_length=maxlen, return_tensors="pt")
+    with torch.amp.autocast(device_type="cuda", dtype=torch.bfloat16, enabled=torch.cuda.is_available()):
+        h = encode_cls(encd)
+        return cls(h)
+
+# ---------------- OOM-safe evaluation ----------------
+def evaluate_set(texts: List[str], labels: List[int], batch: int = INIT_BATCH, maxlen: int = MAXLEN):
+    preds = []
+    i, n = 0, len(texts)
+    while i < n:
+        cur_bs = min(batch, n - i)
+        while True:
+            try:
+                l = logits_for_texts(texts[i:i+cur_bs], maxlen=maxlen)
+                preds.extend(l.argmax(dim=1).cpu().tolist())
+                break
+            except torch.cuda.OutOfMemoryError:
+                memory_guard()
+                if cur_bs <= 1: raise
+                cur_bs = max(1, cur_bs // 2)
+                print(f"[OOM] shrinking batch to {cur_bs}")
+            except RuntimeError as e:
+                if "out of memory" in str(e).lower():
+                    memory_guard()
+                    if cur_bs <= 1: raise
+                    cur_bs = max(1, cur_bs // 2)
+                    print(f"[OOM] shrinking batch to {cur_bs}")
+                else:
+                    raise
+        i += cur_bs
+        batch = cur_bs
+    return {
+        "accuracy": accuracy_score(labels, preds),
+        "macro_f1": f1_score(labels, preds, average="macro"),
+    }
+
+# ---------------- Run JSONL evaluations ----------------
+print_mem("before JSONL eval")
+results = {}
+for jpath in EVAL_FILES:
+    texts, labels = load_eval_jsonl(jpath)
+    print(f"Loaded {jpath}: {len(texts)} rows")
+    metrics = evaluate_set(texts, labels, batch=INIT_BATCH, maxlen=MAXLEN)
+    results[jpath] = metrics
+    print(f"{jpath} -> Acc: {metrics['accuracy']:.4f} | Macro-F1: {metrics['macro_f1']:.4f}")
+
+print("Summary:", results)
+print_mem("done")