The Writer LLM service enables you to customize and use the Writer LLMs outlined below.

ModelParametersAvailabilityLicenseNotes
Palmyra Small128mHuggingFaceApache-2.0Improving language understanding by generative pre-training – arxiv
Palmyra 3B3BHuggingFaceApache-2.0Improving language understanding by generative pre-training – arxiv
Palmyra Base5BHuggingFaceApache-2.0Improving language understanding by generative pre-training – arxiv
Camel 🐪5BHuggingFaceApache-2.0InstructGPT
Palmyra Large20BHuggingFaceApache-2.0Improving language understanding by generative pre-training – arxiv
PalmyraMed20BHuggingFaceApache-2.0Palmyra-Med: Instruction-Based Fine-Tuning of LLMs Enhancing Medical Domain Performance
InstructPalmyra20BHuggingFaceApache-2.0InstructGPT
InstructPalmyra30BAPI, Writer PlatformEnterprise LicenseTraining language models to follow instructions with human feedback
Palmyra-R30BAPI, Writer PlatformEnterprise LicenseAutoregressive language model with Retrieval-Augmented Generation
Palmyra-E30BAPI, Writer PlatformEnterprise LicenseAutoregressive language model
Silk Road----Enterprise License+85K Context Length
Palmyra-X43BAPI, Writer Platform, On-premisesEnterprise LicenseBecoming self-instruct: introducing early stopping criteria for minimal instruct tuning
Palmyra-X43BAPIBeta32K context window
PalmyraMed40BAPI, Writer Platform, On-premisesEnterprise LicensePalmyra-Med: Instruction-Based Fine-Tuning of LLMs Enhancing Medical Domain Performance

These large language models have been pre-trained on a massive amount of Internet text. Pre-training involves taking a mathematical model with random mathematical parameters (weights) and adjusting those weights iteratively in response to discrepancies between the model's output and a comparison point indicating the expected output. The most common training method for large language models is next-word prediction over massive amounts of text.

Differences between models

Palmyra Small

Palmyra Small is the fastest of Writer’s LLMs and can perform important tasks such as text parsing, simple classification, address correction, and keyword recognition. Providing more context drives better performance.

Good at: Text parsing, simple classification, address correction, and keyword recognition

Palmyra Base

Palmyra Base is extremely powerful as well as incredibly fast. This model excels at many nuanced tasks such as sentiment classification and summarization. Palmyra Base is also effective as a general service chatbot, answering questions and performing Q&A.

Competent in: complex classification, text sentiment, and summarization

Camel 🐪

Camel-5b is a trained large language model that follows instructions. Based on Palmyra-Base is trained on ~70k instruction & response fine tuning records generated by Writer Team from the InstructGPT paper, including brainstorming, classification, closed quality assurance, generation, information extraction, open quality assurance, and summarization.

Palmyra Large

Palmyra Large is the most capable model family, capable of performing any task that the other models can, often with less instruction. Palmyra Large is good at comprehending the text's intent, solving logic problems, and explaining character motivations.

Good at: Few-shots, cause and effect, and audience summarization

Instruct​​Palmyra

InstructPalmyra is the most capable model. It can perform any tasks that the other models are able to, often with higher quality, longer output, and better instruction-following.

Good at: Zero-shots, cause and effect

Palmyra-R

Palmyra-R models are a general-purpose fine-tuning recipe for retrieval-augmented generation, combining pre-trained parametric and non-parametric memory for language generation.

Palmyra-E

It is more capable than the GPT-3 and GPT-3.5 models, able to perform more complex tasks, and comes in three flavors: General, Healthcare, and Fintech. It is available on-premise or via an API.

Silk Road

Same capabilities as the Palmyra-E mode but with ~80K context length. still in early testing stage