Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.


license: apache-2.0 language:

  • en pipeline_tag: text-generation

Model Description:

FinSight-Mistral-7B is a large language model fine-tuned on quarterly earnings calls documents to extract financial KPIs. It is based on the Mistral-7B Instruct Architecture.

• Original model: Mistral-7B-Instruct

Dataset Description:-

• Data Source: Yahoo Finance, Factiva

• Data Description: 2K+ Quarterly Earnings Documents

• Data Scope: 200+ publicly listed companies

Prompt template: FinSight -Mistral-7B

Question:

Extract all the finance-based performance indicators and evaluation metrics.

Context:

{context}

Answer:

[/]

Basics:

This section provides information about the model type, version, license, funders, release date and developers. It will be useful for anyone who wants to reference the model.

Model Type: Transformer-based Large Language Model

Version: 1.0

Languages: English

License: Apache 2.0

Cite as: FinSight-Mistral-7B Large Language Model

Technical Specifications:

This section includes details about the model objective and architecture, and the compute infrastructure. It is useful for people interested in model development. Please see the FinSight-Mistral-7B README for full details on replicating training. Model Architecture and Objective

• Modified from Mistral-7B-Instruct

Objective: Financial KPI extraction from quarterly earnings call documents.

Hardware and Software Infrastructure:

• 4 NVIDIA RTX A6000 GPUs

• Environment: PyTorch (pytorch-1.10 w/ CUDA-11.3)

• CPU: Intel(R) Xeon(R) Silver 4216 CPU @ 2.10GHz

• GPU memory: 48GB GDDR6 per GPU

Training:

This section provides information about the training. The following bits and bytes quantization config has been used during training:

• quant_method: bitsandbytes

• load_in_8bit: False

• load_in_4bit: True

• llm_int8_skip_modules: None

• llm_int8_enable_fp32_cpu_offload: False

• llm_int8_has_fp16_weight: False

• bnb_4bit_quant_type: nf4

• bnb_4bit_use_double_quant: True

• bnb_4bit_compute_dtype: float16

• bnb_4bit_use_double_quant= False

Training Dataset:

This section provides a high-level overview of the training data.

Training data includes:

• 200+ Earnings Call Documents

How to Use:

This model can be easily used and deployed using HuggingFace's ecosystem. This needs transformers and accelerate packages installed. The model can be downloaded as follows: FinSight-Mistral-7B

Intended Use:

This model is being created in order to enable public research on large language models (LLMs). LLMs are intended to be used for language generation or as a pre-trained base model that can be further fine-tuned for specific tasks. The use cases below are not exhaustive.

Direct Use:

• Text generation

• Exploring characteristics of language generated by a language model

Downstream Use:

• Tasks that leverage language models include: Information Extraction, Question Answering, Summarization

Out-of-scope Use:

Using the model in high-stakes settings is out of scope for this model. The model is not designed for critical decisions nor uses with any material consequences on an individual's livelihood or wellbeing. The model outputs content that appears factual but may not be correct. Out-of-scope Uses Include: • Usage for evaluating or scoring individuals, such as for employment, education, or credit

• Applying the model for critical automatic decisions, generating factual content, creating reliable summaries, or generating predictions that must be correct

Misuse:

Intentionally using the model for harm, violating human rights, or other kinds of malicious activities, is a misuse of this model. This includes: • Spam generation

• Disinformation and influence operations

• Disparagement and defamation

• Harassment and abuse

• Unconsented impersonation and imitation

• Unconsented surveillance

• Generating content without attribution to the model, as specified in the RAIL License, Use Restrictions

Intended Users:

Direct Users:

• General Public

• Researchers

• Students

• Educators

• Engineers/developers

• Non-commercial entities

• Financial Industry

Risks and Limitations:

This section identifies foreseeable harms and misunderstandings.

Model may:

• Overrepresent some viewpoints and underrepresent others

• Contain stereotypes

• Contain personal information

• Hateful, abusive, or violent language

• Discriminatory or prejudicial language

• Content that may not be appropriate for all settings, including sexual content

• Make errors, including producing incorrect information as if it were factual

• Generate irrelevant or repetitive outputs

• Induce users into attributing human traits to it, such as sentience or consciousness

Evaluation:

This section describes the evaluation protocols and provides the results.

Train-time Evaluation: Final checkpoint after 200 epochs:

• Training Loss: 1.78

Recommendations:

This section provides information on warnings and potential mitigations.

• Indirect users should be made aware when the content they're working with is created by the LLM.

• Users should be aware of Risks and Limitations, and include an appropriate age disclaimer or blocking interface as necessary.

• Users of the model should provide mechanisms for those affected to provide feedback, such as an email address for comments.

Model Card Authors:

Parth Salke

Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
4.97B params
Tensor type
BF16
·
Inference Examples
Unable to determine this model's library. Check the docs .