Model
Model explorer

RedPajama-INCITE-7B-Chat

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

Chat variant fine-tuned on OASST1 + Dolly v2 via OpenChatKit, kept free of distilled proprietary data.

ReasoningCodingVisionFunction callingTool useAgentic
-382.3
Elo · rank #439
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-ChallengeReasoning42.1%#144
best: Llama 3.1 405B · 96.9%
DROPReasoning6.56#70
best: Hunyuan-T1 · 93.1
GSM8KMath0.5%#200
best: Llama 3.1 405B · 96.8%
HellaSwagReasoning70.8%#122
best: Claude 3 Opus · 95.4%
MMLUKnowledge26.9%#278
best: OpenAI o3 · 92.9%
TruthfulQAKnowledge36.1%#91
best: Phi-3.5-MoE (16x3.8B, 6.6B active) · 77.5%
WinoGrandeReasoning59.8%#131
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 2023-470.3RedPajama-INCITE-7B-BaseJun 2023-299.7RedPajama-INCITE-7B-ChatJun 2023-382.3RedPajama-INCITE-7B-InstructJun 2023-300.8
Resources
HFtogethercomputer/RedPajama-INCITE-7B-ChatGHtogethercomputer/OpenChatKitDOCStogether.ai/blog/redpajama-7b
API price weights · each benchmark row carries its own source badge (see methodology)