Model

RedPajama-INCITE-7B-Instruct

OPEN

Together · RedPajama-INCITE family · released Jun 6, 2023

Instruction-tuned 7B; highest-scoring open 7B on HELM at launch (0.492 vs LLaMA-7B's 0.472).

ReasoningCodingVisionFunction callingTool useAgentic

-300.8

Elo · rank #433

Parameters

6.9B

Active params

6.9B (dense)

Context

2K tokens

Architecture

GPT-NeoX / Pythia-style dense transformer

License

Apache-2.0

Languages

—

API price (in/out)

No hosted API

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

ARC-ChallengeReasoning40.8%#147

best: Llama 3.1 405B · 96.9%

ARC-EasyReasoning71.6%#45

best: Phi-3-medium (14B) · 97.7%

DROPReasoning4.21#76

best: Hunyuan-T1 · 93.1

GSM8KMath1.6%#193

best: Llama 3.1 405B · 96.8%

HellaSwagReasoning71.0%#121

best: Claude 3 Opus · 95.4%

LAMBADAReasoning69.0%#21

best: GPT-3 175B · 86.4%

MMLUKnowledge36.6%#262

best: OpenAI o3 · 92.9%

OpenBookQAReasoning48.8%#28

best: Claude 1 · 90.8%

PIQAReasoning77.0%#63

best: GPT-4o mini · 93.1%

TruthfulQAKnowledge22.6%#108

best: Phi-3.5-MoE (16x3.8B, 6.6B active) · 77.5%

WinoGrandeReasoning65.7%#116

best: PaLM 2 · 90.9%

Run it locally

VRAM @ Q4

5 GB

VRAM @ FP16

14 GB

Fits on (Q4)

RTX 3060 12GBRTX 4070 Ti 16GBRTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB

Throughput data unavailable.

Quantizations

GGUF Q4

RedPajama-INCITE family

Elo progression across releases

RedPajama-INCITE-Base-3B-v1May 2023-470.3 RedPajama-INCITE-7B-BaseJun 2023-299.7 RedPajama-INCITE-7B-ChatJun 2023-382.3 RedPajama-INCITE-7B-InstructJun 2023-300.8

Resources

HFtogethercomputer/RedPajama-INCITE-7B-Instruct DOCStogether.ai/blog/redpajama-7b

API price weights · each benchmark row carries its own source badge (see methodology)