MASHQA-Mistral-7B-Instruct

Model Description

MASHQA-Mistral-7B-Instruct is a large language model fine-tuned on healthcare question-answer pairs to respond safely to the users' queries. It is based on the Mistral-7B Instruct Architecture.

Original model: Mistral-7B-Instruct

Dataset Description

Data Source: MASHQA (Multiple Answer Spans Healthcare Question Answering) Data
Data Description: Multiple question-answer pairs in JSON format.

Prompt template

[INST]Act as a Multiple Answer Spans Healthcare Question Answering helpful assistant and answer the user's questions in details with reasoning. Do not give any false information. In case you don't have answer, specify why the question can't be answered.
    
### Question:
{question}

### Answer:

Basics

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

Model Type: Transformer-based Large Language Model

Version: 1.0.0

Languages: English

License: Apache 2.0

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.

Model Architecture and Objective

Modified from Mistral-7B-Instruct

Objective: Safely respond to users' health-related queries.

Training

This section provides information about the training. It is useful for people who want to learn more about the model inputs and training footprint.

The following bits and bytes quantization config was used during training:

quant_method: bitsandbytes
load_in_8bit: False
load_in_4bit: True
llm_int8_threshold: 6.0
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

Framework versions

PEFT 0.4.0

How to use

This model can be easily used and deployed using HuggingFace's ecosystem. This needs transformers and accelerate installed. The model can be downloaded as follows:

MASHQA-Mistral-7B-Instruct

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
- Examples: Cloze tests, counterfactuals, generations with reframings

Downstream Use

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

Out-of-scope Uses

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
Deception
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
Health Industry

Risks and Limitations

This section identifies foreseeable harms and misunderstandings.

Model may:

Overrepresent some viewpoints and underrepresent others
Contain stereotypes
Contain personal information
Generate:
- 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 500 epochs:

Training Loss: 1.216

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

Mohd Zeeshan