Update README.md

7584a28 verified 4 months ago

23.3 kB

	---
	base_model: meta-llama/Meta-Llama-3-8B
	datasets:
	- 2024-mcm-everitt-ryan/job-bias-synthetic-human-benchmark-v2
	language: en
	license: apache-2.0
	model_id: Meta-Llama-3-8B-job-bias-qlora-seq-cls
	model_description: The model is a multi-label classifier designed to detect various
	types of bias within job descriptions.
	developers: Tristan Everitt and Paul Ryan
	model_card_authors: See developers
	model_card_contact: See developers
	repo: https://gitlab.computing.dcu.ie/everitt2/2024-mcm-everitt-ryan
	training_regime: 'accelerator_config="{''split_batches'': False, ''dispatch_batches'':
	None, ''even_batches'': True, ''use_seedable_sampler'': True, ''non_blocking'':
	False, ''gradient_accumulation_kwargs'': None}", adafactor=false, adam_beta1=0.9,
	adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=false, batch_eval_metrics=false,
	bf16=false, bf16_full_eval=false, data_seed="None", dataloader_drop_last=false,
	dataloader_num_workers=0, dataloader_persistent_workers=false, dataloader_pin_memory=true,
	dataloader_prefetch_factor="None", ddp_backend="None", ddp_broadcast_buffers="None",
	ddp_bucket_cap_mb="None", ddp_find_unused_parameters="None", ddp_timeout=1800, deepspeed="None",
	disable_tqdm=false, dispatch_batches="None", do_eval=true, do_predict=false, do_train=false,
	eval_accumulation_steps="None", eval_batch_size=8, eval_delay=0, eval_do_concat_batches=true,
	eval_on_start=false, eval_steps="None", eval_strategy="epoch", evaluation_strategy="None",
	fp16=false, fp16_backend="auto", fp16_full_eval=false, fp16_opt_level="O1", fsdp="[]",
	fsdp_config="{''min_num_params'': 0, ''xla'': False, ''xla_fsdp_v2'': False, ''xla_fsdp_grad_ckpt'':
	False}", fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap="None", full_determinism=false,
	gradient_accumulation_steps=1, gradient_checkpointing="(False,)", gradient_checkpointing_kwargs="None",
	greater_is_better=false, group_by_length=true, half_precision_backend="auto", ignore_data_skip=false,
	include_inputs_for_metrics=false, jit_mode_eval=false, label_names="None", label_smoothing_factor=0.0,
	learning_rate=0.0001, length_column_name="length", load_best_model_at_end=true,
	local_rank=0, lr_scheduler_kwargs="{}", lr_scheduler_type="linear", max_grad_norm=1.0,
	max_steps=-1, metric_for_best_model="loss", mp_parameters="", neftune_noise_alpha="None",
	no_cuda=false, num_train_epochs=3, optim="adamw_torch", optim_args="None", optim_target_modules="None",
	past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=8, per_gpu_eval_batch_size="None",
	per_gpu_train_batch_size="None", prediction_loss_only=false, ray_scope="last", remove_unused_columns=true,
	report_to="[]", restore_callback_states_from_checkpoint=false, resume_from_checkpoint="None",
	seed=42, skip_memory_metrics=true, split_batches="None", tf32="None", torch_compile=false,
	torch_compile_backend="None", torch_compile_mode="None", torchdynamo="None", tpu_num_cores="None",
	train_batch_size=8, use_cpu=false, use_ipex=false, use_legacy_prediction_loop=false,
	use_mps_device=false, warmup_ratio=0.0, warmup_steps=0, weight_decay=0.001'
	results: " precision recall f1-score support\n \n \
	\ age 0.91 0.36 0.52 80\n disability 0.97\
	\ 0.46 0.63 80\n feminine 1.00 0.88 0.93\
	\ 80\n general 0.75 0.51 0.61 80\n masculine\
	\ 0.93 0.53 0.67 80\n neutral 0.32 0.86\
	\ 0.47 80\n racial 0.97 0.76 0.85 80\n\
	\ sexuality 0.94 0.75 0.83 80\n \n micro avg\
	\ 0.71 0.64 0.67 640\n macro avg 0.85 0.64\
	\ 0.69 640\n weighted avg 0.85 0.64 0.69 640\n\
	\ samples avg 0.67 0.69 0.68 640\n "
	compute_infrastructure: '- Linux 6.5.0-35-generic x86_64

	- MemTotal: 1056613768 kB

	- 256 X AMD EPYC 7702 64-Core Processor

	- GPU_0: NVIDIA L40S'
	software: python 3.10.12, accelerate 0.32.1, aiohttp 3.9.5, aiosignal 1.3.1, anyio
	4.2.0, argon2-cffi 23.1.0, argon2-cffi-bindings 21.2.0, arrow 1.3.0, asttokens 2.4.1,
	async-lru 2.0.4, async-timeout 4.0.3, attrs 23.2.0, awscli 1.33.26, Babel 2.14.0,
	beautifulsoup4 4.12.3, bitsandbytes 0.43.1, bleach 6.1.0, blinker 1.4, botocore
	1.34.144, certifi 2024.2.2, cffi 1.16.0, charset-normalizer 3.3.2, click 8.1.7,
	cloudpickle 3.0.0, colorama 0.4.6, comm 0.2.1, cryptography 3.4.8, dask 2024.7.0,
	datasets 2.20.0, dbus-python 1.2.18, debugpy 1.8.0, decorator 5.1.1, defusedxml
	0.7.1, dill 0.3.8, distro 1.7.0, docutils 0.16, einops 0.8.0, entrypoints 0.4, evaluate
	0.4.2, exceptiongroup 1.2.0, executing 2.0.1, fastjsonschema 2.19.1, filelock 3.13.1,
	flash-attn 2.6.1, fqdn 1.5.1, frozenlist 1.4.1, fsspec 2024.2.0, h11 0.14.0, hf_transfer
	0.1.6, httpcore 1.0.2, httplib2 0.20.2, httpx 0.26.0, huggingface-hub 0.23.4, idna
	3.6, importlib_metadata 8.0.0, iniconfig 2.0.0, ipykernel 6.29.0, ipython 8.21.0,
	ipython-genutils 0.2.0, ipywidgets 8.1.1, isoduration 20.11.0, jedi 0.19.1, jeepney
	0.7.1, Jinja2 3.1.3, jmespath 1.0.1, joblib 1.4.2, json5 0.9.14, jsonpointer 2.4,
	jsonschema 4.21.1, jsonschema-specifications 2023.12.1, jupyter-archive 3.4.0, jupyter_client
	7.4.9, jupyter_contrib_core 0.4.2, jupyter_contrib_nbextensions 0.7.0, jupyter_core
	5.7.1, jupyter-events 0.9.0, jupyter-highlight-selected-word 0.2.0, jupyter-lsp
	2.2.2, jupyter-nbextensions-configurator 0.6.3, jupyter_server 2.12.5, jupyter_server_terminals
	0.5.2, jupyterlab 4.1.0, jupyterlab_pygments 0.3.0, jupyterlab_server 2.25.2, jupyterlab-widgets
	3.0.9, keyring 23.5.0, launchpadlib 1.10.16, lazr.restfulclient 0.14.4, lazr.uri
	1.0.6, locket 1.0.0, lxml 5.1.0, MarkupSafe 2.1.5, matplotlib-inline 0.1.6, mistune
	3.0.2, more-itertools 8.10.0, mpmath 1.3.0, multidict 6.0.5, multiprocess 0.70.16,
	nbclassic 1.0.0, nbclient 0.9.0, nbconvert 7.14.2, nbformat 5.9.2, nest-asyncio
	1.6.0, networkx 3.2.1, nltk 3.8.1, notebook 6.5.5, notebook_shim 0.2.3, numpy 1.26.3,
	nvidia-cublas-cu12 12.1.3.1, nvidia-cuda-cupti-cu12 12.1.105, nvidia-cuda-nvrtc-cu12
	12.1.105, nvidia-cuda-runtime-cu12 12.1.105, nvidia-cudnn-cu12 8.9.2.26, nvidia-cufft-cu12
	11.0.2.54, nvidia-curand-cu12 10.3.2.106, nvidia-cusolver-cu12 11.4.5.107, nvidia-cusparse-cu12
	12.1.0.106, nvidia-nccl-cu12 2.19.3, nvidia-nvjitlink-cu12 12.3.101, nvidia-nvtx-cu12
	12.1.105, oauthlib 3.2.0, overrides 7.7.0, packaging 23.2, pandas 2.2.2, pandocfilters
	1.5.1, parso 0.8.3, partd 1.4.2, peft 0.11.1, pexpect 4.9.0, pillow 10.2.0, pip
	24.1.2, platformdirs 4.2.0, pluggy 1.5.0, polars 1.1.0, prometheus-client 0.19.0,
	prompt-toolkit 3.0.43, protobuf 5.27.2, psutil 5.9.8, ptyprocess 0.7.0, pure-eval
	0.2.2, pyarrow 16.1.0, pyarrow-hotfix 0.6, pyasn1 0.6.0, pycparser 2.21, Pygments
	2.17.2, PyGObject 3.42.1, PyJWT 2.3.0, pyparsing 2.4.7, pytest 8.2.2, python-apt
	2.4.0+ubuntu3, python-dateutil 2.8.2, python-json-logger 2.0.7, pytz 2024.1, PyYAML
	6.0.1, pyzmq 24.0.1, referencing 0.33.0, regex 2024.5.15, requests 2.32.3, rfc3339-validator
	0.1.4, rfc3986-validator 0.1.1, rpds-py 0.17.1, rsa 4.7.2, s3transfer 0.10.2, safetensors
	0.4.3, scikit-learn 1.5.1, scipy 1.14.0, SecretStorage 3.3.1, Send2Trash 1.8.2,
	sentence-transformers 3.0.1, sentencepiece 0.2.0, setuptools 69.0.3, six 1.16.0,
	sniffio 1.3.0, soupsieve 2.5, stack-data 0.6.3, sympy 1.12, tabulate 0.9.0, terminado
	0.18.0, threadpoolctl 3.5.0, tiktoken 0.7.0, tinycss2 1.2.1, tokenizers 0.19.1,
	tomli 2.0.1, toolz 0.12.1, torch 2.2.0, torchaudio 2.2.0, torchdata 0.7.1, torchtext
	0.17.0, torchvision 0.17.0, tornado 6.4, tqdm 4.66.4, traitlets 5.14.1, transformers
	4.42.4, triton 2.2.0, types-python-dateutil 2.8.19.20240106, typing_extensions 4.9.0,
	tzdata 2024.1, uri-template 1.3.0, urllib3 2.2.2, wadllib 1.3.6, wcwidth 0.2.13,
	webcolors 1.13, webencodings 0.5.1, websocket-client 1.7.0, wheel 0.42.0, widgetsnbextension
	4.0.9, xxhash 3.4.1, yarl 1.9.4, zipp 1.0.0
	hardware_type: 1 X NVIDIA L40S
	hours_used: '4.43'
	cloud_provider: N/A
	cloud_region: N/A
	co2_emitted: N/A
	direct_use: "\n ```python\n from transformers import pipeline\n\n pipe =\
	\ pipeline(\"text-classification\", model=\"2024-mcm-everitt-ryan/Meta-Llama-3-8B-job-bias-qlora-seq-cls\"\
	, return_all_scores=True)\n\n results = pipe(\"Join our dynamic and fast-paced\
	\ team as a Junior Marketing Specialist. We seek a tech-savvy and energetic individual\
	\ who thrives in a vibrant environment. Ideal candidates are digital natives with\
	\ a fresh perspective, ready to adapt quickly to new trends. You should have recent\
	\ experience in social media strategies and a strong understanding of current digital\
	\ marketing tools. We're looking for someone with a youthful mindset, eager to bring\
	\ innovative ideas to our young and ambitious team. If you're a recent graduate\
	\ or early in your career, this opportunity is perfect for you!\")\n print(results)\n\
	\ ```\n >> [[\n {'label': 'age', 'score': 0.9883460402488708}, \n {'label':\
	\ 'disability', 'score': 0.00787709467113018}, \n {'label': 'feminine', 'score':\
	\ 0.007224376779049635}, \n {'label': 'general', 'score': 0.09967829287052155},\
	\ \n {'label': 'masculine', 'score': 0.0035264550242573023}, \n {'label':\
	\ 'racial', 'score': 0.014618005603551865}, \n {'label': 'sexuality', 'score':\
	\ 0.005568435415625572}\n ]]\n "
	model-index:
	- name: Meta-Llama-3-8B-job-bias-qlora-seq-cls
	results:
	- task:
	type: multi_label_classification
	dataset:
	name: 2024-mcm-everitt-ryan/job-bias-synthetic-human-benchmark-v2
	type: mix_human-eval_synthetic
	metrics:
	- type: loss
	value: 0.37650468945503235
	- type: accuracy
	value: 0.6472602739726028
	- type: f1_micro
	value: 0.6704918032786885
	- type: precision_micro
	value: 0.7051724137931035
	- type: recall_micro
	value: 0.6390625
	- type: roc_auc_micro
	value: 0.7983258928571428
	- type: f1_macro
	value: 0.6893983094047521
	- type: precision_macro
	value: 0.8485524649424994
	- type: recall_macro
	value: 0.6390625000000001
	- type: roc_auc_macro
	value: 0.7983258928571428
	- type: f1_samples
	value: 0.6797374429223745
	- type: precision_samples
	value: 0.6743721461187215
	- type: recall_samples
	value: 0.6936358447488585
	- type: roc_auc_samples
	value: 0.8250713470319635
	- type: f1_weighted
	value: 0.6893983094047522
	- type: precision_weighted
	value: 0.8485524649424991
	- type: recall_weighted
	value: 0.6390625
	- type: roc_auc_weighted
	value: 0.7983258928571428
	- type: runtime
	value: 266.7981
	- type: samples_per_second
	value: 2.189
	- type: steps_per_second
	value: 0.274
	- type: epoch
	value: 3.0
	---

	# Model Card for Meta-Llama-3-8B-job-bias-qlora-seq-cls

	<!-- Provide a quick summary of what the model is/does. -->



	## Model Details

	<!-- Provide a longer summary of what this model is. -->

	The model is a multi-label classifier designed to detect various types of bias within job descriptions.

	- Developed by: Tristan Everitt and Paul Ryan
	- Model type: Decoder
	- Language(s) (NLP): en
	- License: apache-2.0
	- Finetuned from model: meta-llama/Meta-Llama-3-8B

	### Model Sources

	- Repository: https://github.com/2024-mcm-everitt-ryan
	- Paper: In Progress

	## Uses

	The primary target audience for these models are researchers dedicated to identifying biased language in job descriptions.

	### Out-of-Scope Use

	Due to the limitations inherent in large-scale language models, they should not be utilised in applications requiring factual or accurate outputs. These models do not distinguish between fact and fiction, and implicit biases are inherently subjective.

	Moreover, as language models mirror the biases present in their training data, they should not be deployed in systems that directly interact with humans unless the deployers have first conducted a thorough analysis of relevant biases for the specific use case.

	## Bias, Risks, and Limitations

	It is imperative that all users, both direct and downstream, are aware of the risks, biases, and limitations associated with this model. Important considerations include:

	- Bias in Training Data: The model may inherit and perpetuate biases from the data it was trained on.
	- Subjectivity of Bias: Bias detection is inherently subjective, and perceptions of bias can differ across contexts and users.
	- Accuracy Concerns: The model’s outputs are not guaranteed to be true or accurate, making it unsuitable for applications that require reliable information.
	- Human Interaction Risks: When incorporated into systems that interact with humans, the model’s biases may affect interactions and decision-making, potentially leading to unintended consequences.

	It is crucial for users to conduct comprehensive evaluations and consider these factors when applying the model in any context.


	## How to Get Started with the Model

	Use the code below to get started with the model.


	```python
	from transformers import pipeline

	pipe = pipeline("text-classification", model="2024-mcm-everitt-ryan/Meta-Llama-3-8B-job-bias-qlora-seq-cls", return_all_scores=True)

	results = pipe("Join our dynamic and fast-paced team as a Junior Marketing Specialist. We seek a tech-savvy and energetic individual who thrives in a vibrant environment. Ideal candidates are digital natives with a fresh perspective, ready to adapt quickly to new trends. You should have recent experience in social media strategies and a strong understanding of current digital marketing tools. We're looking for someone with a youthful mindset, eager to bring innovative ideas to our young and ambitious team. If you're a recent graduate or early in your career, this opportunity is perfect for you!")
	print(results)
	```
	>> [[
	{'label': 'age', 'score': 0.9883460402488708},
	{'label': 'disability', 'score': 0.00787709467113018},
	{'label': 'feminine', 'score': 0.007224376779049635},
	{'label': 'general', 'score': 0.09967829287052155},
	{'label': 'masculine', 'score': 0.0035264550242573023},
	{'label': 'racial', 'score': 0.014618005603551865},
	{'label': 'sexuality', 'score': 0.005568435415625572}
	]]


	## 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. -->

	- [2024-mcm-everitt-ryan/benchmark](https://huggingface.co/datasets/2024-mcm-everitt-ryan/benchmark)


	#### Training Hyperparameters

	accelerator_config="{'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}", adafactor=false, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=false, batch_eval_metrics=false, bf16=false, bf16_full_eval=false, data_seed="None", dataloader_drop_last=false, dataloader_num_workers=0, dataloader_persistent_workers=false, dataloader_pin_memory=true, dataloader_prefetch_factor="None", ddp_backend="None", ddp_broadcast_buffers="None", ddp_bucket_cap_mb="None", ddp_find_unused_parameters="None", ddp_timeout=1800, deepspeed="None", disable_tqdm=false, dispatch_batches="None", do_eval=true, do_predict=false, do_train=false, eval_accumulation_steps="None", eval_batch_size=8, eval_delay=0, eval_do_concat_batches=true, eval_on_start=false, eval_steps="None", eval_strategy="epoch", evaluation_strategy="None", fp16=false, fp16_backend="auto", fp16_full_eval=false, fp16_opt_level="O1", fsdp="[]", fsdp_config="{'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}", fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap="None", full_determinism=false, gradient_accumulation_steps=1, gradient_checkpointing="(False,)", gradient_checkpointing_kwargs="None", greater_is_better=false, group_by_length=true, half_precision_backend="auto", ignore_data_skip=false, include_inputs_for_metrics=false, jit_mode_eval=false, label_names="None", label_smoothing_factor=0.0, learning_rate=0.0001, length_column_name="length", load_best_model_at_end=true, local_rank=0, lr_scheduler_kwargs="{}", lr_scheduler_type="linear", max_grad_norm=1.0, max_steps=-1, metric_for_best_model="loss", mp_parameters="", neftune_noise_alpha="None", no_cuda=false, num_train_epochs=3, optim="adamw_torch", optim_args="None", optim_target_modules="None", past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=8, per_gpu_eval_batch_size="None", per_gpu_train_batch_size="None", prediction_loss_only=false, ray_scope="last", remove_unused_columns=true, report_to="[]", restore_callback_states_from_checkpoint=false, resume_from_checkpoint="None", seed=42, skip_memory_metrics=true, split_batches="None", tf32="None", torch_compile=false, torch_compile_backend="None", torch_compile_mode="None", torchdynamo="None", tpu_num_cores="None", train_batch_size=8, use_cpu=false, use_ipex=false, use_legacy_prediction_loop=false, use_mps_device=false, warmup_ratio=0.0, warmup_steps=0, weight_decay=0.001 <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->


	## Results

	precision recall f1-score support

	age 0.91 0.36 0.52 80
	disability 0.97 0.46 0.63 80
	feminine 1.00 0.88 0.93 80
	general 0.75 0.51 0.61 80
	masculine 0.93 0.53 0.67 80
	neutral 0.32 0.86 0.47 80
	racial 0.97 0.76 0.85 80
	sexuality 0.94 0.75 0.83 80

	micro avg 0.71 0.64 0.67 640
	macro avg 0.85 0.64 0.69 640
	weighted avg 0.85 0.64 0.69 640
	samples avg 0.67 0.69 0.68 640


	## 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: 1 X NVIDIA L40S
	- Hours used: 4.43
	- Cloud Provider: N/A
	- Compute Region: N/A
	- Carbon Emitted: N/A

	### Compute Infrastructure

	- Linux 6.5.0-35-generic x86_64
	- MemTotal: 1056613768 kB
	- 256 X AMD EPYC 7702 64-Core Processor
	- GPU_0: NVIDIA L40S

	#### Software

	python 3.10.12, accelerate 0.32.1, aiohttp 3.9.5, aiosignal 1.3.1, anyio 4.2.0, argon2-cffi 23.1.0, argon2-cffi-bindings 21.2.0, arrow 1.3.0, asttokens 2.4.1, async-lru 2.0.4, async-timeout 4.0.3, attrs 23.2.0, awscli 1.33.26, Babel 2.14.0, beautifulsoup4 4.12.3, bitsandbytes 0.43.1, bleach 6.1.0, blinker 1.4, botocore 1.34.144, certifi 2024.2.2, cffi 1.16.0, charset-normalizer 3.3.2, click 8.1.7, cloudpickle 3.0.0, colorama 0.4.6, comm 0.2.1, cryptography 3.4.8, dask 2024.7.0, datasets 2.20.0, dbus-python 1.2.18, debugpy 1.8.0, decorator 5.1.1, defusedxml 0.7.1, dill 0.3.8, distro 1.7.0, docutils 0.16, einops 0.8.0, entrypoints 0.4, evaluate 0.4.2, exceptiongroup 1.2.0, executing 2.0.1, fastjsonschema 2.19.1, filelock 3.13.1, flash-attn 2.6.1, fqdn 1.5.1, frozenlist 1.4.1, fsspec 2024.2.0, h11 0.14.0, hf_transfer 0.1.6, httpcore 1.0.2, httplib2 0.20.2, httpx 0.26.0, huggingface-hub 0.23.4, idna 3.6, importlib_metadata 8.0.0, iniconfig 2.0.0, ipykernel 6.29.0, ipython 8.21.0, ipython-genutils 0.2.0, ipywidgets 8.1.1, isoduration 20.11.0, jedi 0.19.1, jeepney 0.7.1, Jinja2 3.1.3, jmespath 1.0.1, joblib 1.4.2, json5 0.9.14, jsonpointer 2.4, jsonschema 4.21.1, jsonschema-specifications 2023.12.1, jupyter-archive 3.4.0, jupyter_client 7.4.9, jupyter_contrib_core 0.4.2, jupyter_contrib_nbextensions 0.7.0, jupyter_core 5.7.1, jupyter-events 0.9.0, jupyter-highlight-selected-word 0.2.0, jupyter-lsp 2.2.2, jupyter-nbextensions-configurator 0.6.3, jupyter_server 2.12.5, jupyter_server_terminals 0.5.2, jupyterlab 4.1.0, jupyterlab_pygments 0.3.0, jupyterlab_server 2.25.2, jupyterlab-widgets 3.0.9, keyring 23.5.0, launchpadlib 1.10.16, lazr.restfulclient 0.14.4, lazr.uri 1.0.6, locket 1.0.0, lxml 5.1.0, MarkupSafe 2.1.5, matplotlib-inline 0.1.6, mistune 3.0.2, more-itertools 8.10.0, mpmath 1.3.0, multidict 6.0.5, multiprocess 0.70.16, nbclassic 1.0.0, nbclient 0.9.0, nbconvert 7.14.2, nbformat 5.9.2, nest-asyncio 1.6.0, networkx 3.2.1, nltk 3.8.1, notebook 6.5.5, notebook_shim 0.2.3, numpy 1.26.3, nvidia-cublas-cu12 12.1.3.1, nvidia-cuda-cupti-cu12 12.1.105, nvidia-cuda-nvrtc-cu12 12.1.105, nvidia-cuda-runtime-cu12 12.1.105, nvidia-cudnn-cu12 8.9.2.26, nvidia-cufft-cu12 11.0.2.54, nvidia-curand-cu12 10.3.2.106, nvidia-cusolver-cu12 11.4.5.107, nvidia-cusparse-cu12 12.1.0.106, nvidia-nccl-cu12 2.19.3, nvidia-nvjitlink-cu12 12.3.101, nvidia-nvtx-cu12 12.1.105, oauthlib 3.2.0, overrides 7.7.0, packaging 23.2, pandas 2.2.2, pandocfilters 1.5.1, parso 0.8.3, partd 1.4.2, peft 0.11.1, pexpect 4.9.0, pillow 10.2.0, pip 24.1.2, platformdirs 4.2.0, pluggy 1.5.0, polars 1.1.0, prometheus-client 0.19.0, prompt-toolkit 3.0.43, protobuf 5.27.2, psutil 5.9.8, ptyprocess 0.7.0, pure-eval 0.2.2, pyarrow 16.1.0, pyarrow-hotfix 0.6, pyasn1 0.6.0, pycparser 2.21, Pygments 2.17.2, PyGObject 3.42.1, PyJWT 2.3.0, pyparsing 2.4.7, pytest 8.2.2, python-apt 2.4.0+ubuntu3, python-dateutil 2.8.2, python-json-logger 2.0.7, pytz 2024.1, PyYAML 6.0.1, pyzmq 24.0.1, referencing 0.33.0, regex 2024.5.15, requests 2.32.3, rfc3339-validator 0.1.4, rfc3986-validator 0.1.1, rpds-py 0.17.1, rsa 4.7.2, s3transfer 0.10.2, safetensors 0.4.3, scikit-learn 1.5.1, scipy 1.14.0, SecretStorage 3.3.1, Send2Trash 1.8.2, sentence-transformers 3.0.1, sentencepiece 0.2.0, setuptools 69.0.3, six 1.16.0, sniffio 1.3.0, soupsieve 2.5, stack-data 0.6.3, sympy 1.12, tabulate 0.9.0, terminado 0.18.0, threadpoolctl 3.5.0, tiktoken 0.7.0, tinycss2 1.2.1, tokenizers 0.19.1, tomli 2.0.1, toolz 0.12.1, torch 2.2.0, torchaudio 2.2.0, torchdata 0.7.1, torchtext 0.17.0, torchvision 0.17.0, tornado 6.4, tqdm 4.66.4, traitlets 5.14.1, transformers 4.42.4, triton 2.2.0, types-python-dateutil 2.8.19.20240106, typing_extensions 4.9.0, tzdata 2024.1, uri-template 1.3.0, urllib3 2.2.2, wadllib 1.3.6, wcwidth 0.2.13, webcolors 1.13, webencodings 0.5.1, websocket-client 1.7.0, wheel 0.42.0, widgetsnbextension 4.0.9, xxhash 3.4.1, yarl 1.9.4, zipp 1.0.0

	## Citation

	<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

	BibTeX:

	In Progress