Llama 3 Swallow 70B Instruct

About

Japanese bilingual model from Tokyo Tech, fine-tuned from Llama 3 70B.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

Providers(1)

Provider	Input (per 1M)	Output (per 1M)	Type
NVIDIA NIM	—	—	Serverless

Rankings

Best Open Source LLMs Cheapest LLM APIs

Compare

All comparisons →

Llama 3 Swallow 70B Instruct vs Qwen2 7B Instruct Llama 3 Swallow 70B Instruct vs ShieldGemma 9B Llama 3 Swallow 70B Instruct vs Dracarys Llama 3.1 70B Instruct Llama 3 Swallow 70B Instruct vs Gemma 2 9B SahabatAI Instruct Llama 3 Swallow 70B Instruct vs Llama 3 Taiwan 70B Instruct Llama 3 Swallow 70B Instruct vs Bielik 11B v2.6 Instruct Llama 3 Swallow 70B Instruct vs Sarvam-M Multilingual Hybrid Llama 3 Swallow 70B Instruct vs Teuken 7B Instruct Llama 3 Swallow 70B Instruct vs Italia 10B Instruct Llama 3 Swallow 70B Instruct vs Colosseum 355B Instruct Llama 3 Swallow 70B Instruct vs Stockmark 2 100B Instruct Llama 3 Swallow 70B Instruct vs Seed-OSS 36B Instruct Llama 3 Swallow 70B Instruct vs Marin 8B Instruct Llama 3 Swallow 70B Instruct vs Granite Guardian 3.0 8B Llama 3 Swallow 70B Instruct vs Falcon 3 7B Instruct Llama 3 Swallow 70B Instruct vs Llama 3.2 NV RerankQA 1B v2

Specifications

Released2024-06-01

Parameters70B

Context4K

ArchitectureDecoder Only

Specializationgeneral

Trainingpretraining

Fine-tuninginstruction_tuning

Providers(1)