Llama-v3-ELYZA-JP-8B
State‑of‑the‑art large language model useful on a variety of language understanding and generation tasks.
Llama‑3‑ELYZA‑JP‑8B is a lightweight LLM with only 8 billion parameters, yet achieves Japanese language performance comparable to GPT‑3.5 Turbo. The model has undergone additional pre‑training and post‑training of Japanese to expand instruction‑following capabilities in Japanese.
Technical Details
Input sequence length for Prompt Processor:128
Maximum context length:4096
Precision:w4a16 + w8a16 (few layers)
Supported languages:Japanese
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 (4096 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
License
Model:LLAMA3
Terms of Use:Qualcomm® Generative AI usage and limitations
Tags
- llm
- generative-ai
Supported Mobile Devices
- Snapdragon 8 Elite Gen 5 QRD
- Snapdragon 8 Elite QRD
Supported Mobile Chipsets
- Snapdragon® 8 Elite Mobile
- Snapdragon® 8 Elite Gen 5 Mobile
Related Models
See all models
Looking for more? See models created by industry leaders.
Discover Model Makers