Qualcomm® AI HubAI Hub

JAIS-6p7b-Chat

State‑of‑the‑art large language model useful on a variety of language understanding and generation tasks.

JAIS 6.7B is a bilingual large language model (LLM) for both Arabic and English developed by Inception, a G42 company in partnership with MBZUAI and Cerebras. This is a 6.7 billion parameter LLM, trained on a dataset containing 141 billion Arabic tokens and 339 billion English/code tokens. The model is based on transformer‑based decoder‑only (GPT‑3) architecture and uses SwiGLU non‑linearity. It implements ALiBi position embeddings, enabling the model to extrapolate to long sequence lengths, providing improved context handling and model precision. The JAIS family of models is a comprehensive series of bilingual English‑Arabic LLMs. These models are optimized to excel in Arabic while having strong English capabilities.

Technical Details

Input sequence length for Prompt Processor:128
Max context length:2048
Number of parameters:6.7B
Precision:w4a16 + w8a16 (a few layers)
Use:Initiate conversation with prompt-processor and then token generator for subsequent iterations.
Supported languages:Arabic (MSA) and English.
Minimum QNN SDK version required:2.27.7
TTFT:Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (2048 tokens).
Response Rate:Rate of response generation after the first response token.

Applicable Scenarios

  • Dialogue
  • Content Generation
  • Customer Support

Supported Mobile Form Factors

  • Phone
  • Tablet

Licenses

Tags

  • llm
  • generative-ai
  • quantized

Supported Mobile Devices

  • Snapdragon 8 Elite QRD

Supported Mobile Chipsets

  • Snapdragon® 8 Elite Mobile

Models from G42

See all model makers

Looking for more? See pre‑optimized models for all solutions.

Browse All