Panther
Rardilit Large Open-access Language Model
Model Card
Version 1.0 / 29.May.2023
Model Card for Bloom-560m
Table of Contents
Model Details
Model Description
This section provides information for anyone who wants to know about the model.
Developed by: Rardilit (website)
- All collaborators are either volunteers or have an agreement with their employer. (Further breakdown of participants forthcoming.)
Model Type: Transformer-based Language Model
Version: 1.0.0
Languages: Multiple;
License: Panther License v1.0 (link)
Release Date Estimate: Monday, 16.May.2023
Uses
This section addresses questions around how the model is intended to be used, discusses the foreseeable users of the model (including those affected by the model), and describes uses that are considered out of scope or misuse of the model. It provides information for anyone considering using the model or who is affected by the model.
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 pretrained base model that can be further fine-tuned for specific tasks. 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
Misuse and Out-of-scope Use
This section addresses what users ought not do with the model.
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 is not correct.
Out-of-scope Uses Include:
Usage in biomedical domains, political and legal domains, or finance domains
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
Intended Users
Direct Users
General Public
Researchers
Students
Educators
Engineers/developers
Non-commercial entities
Community advocates, including human and civil rights groups
Indirect Users
- Users of derivatives created by Direct Users, such as those using software with an intended use
Others Affected (Parties Prenantes)
People and groups referred to by the LLM
People and groups exposed to outputs of, or decisions based on, the LLM
People and groups whose original work is included in the LLM
Bias, 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
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.
Models pretrained with the LLM should include an updated Model Card.
Users of the model should provide mechanisms for those affected to provide feedback, such as an email address for comments.
Training Details
This repo contains a low-rank adapter for LLaMA-7b with just 4194304 parameters fit on the Rardilit/Panther-dataset_v1 dataset with 20k prompts and responses.
This version of the weights was trained with the following hyperparameters:
Epochs: 1 (load from best epoch)
LORA_R = 8
LORA_ALPHA = 16
LORA_DROPOUT= 0.05
LORA_TARGET_MODULES = [ "q_proj", "v_proj", ]
BATCH_SIZE = 300
MICRO_BATCH_SIZE = 4
GRADIENT_ACCUMULATION_STEPS = BATCH_SIZE // MICRO_BATCH_SIZE
LEARNING_RATE = 3e-4
TRAIN_STEPS = 10
warmup_steps = 10
logging_steps = 1
fp16 = true
optim = "adamw_torch"
eval_steps=4
save_steps=8
Training Time
The time in training this model with 1 x T4 16gb vRAM was approx. 45 min.
- Downloads last month
- 720