llama3-chatqa

106.3K 1 year ago

A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

8b 70b

35 models

llama3-chatqa:latest
b37a98d204b2 • 4.7GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b latest
b37a98d204b2 • 4.7GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b
ab8941f03aa3 • 40GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5
b37a98d204b2 • 4.7GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q2_K
010674c8ebb4 • 3.2GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q3_K_S
6d4cf2ccd7df • 3.7GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q3_K_M
d1cbce0911ee • 4.0GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q3_K_L
748c33a3a51f • 4.3GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q4_0
b37a98d204b2 • 4.7GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q4_1
598e30318446 • 5.1GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q4_K_S
c4c5c98e11c6 • 4.7GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q4_K_M
07e385a3991b • 4.9GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q5_0
7775bf791816 • 5.6GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q5_1
233019c7a259 • 6.1GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q5_K_S
3eab2a2fa684 • 5.6GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q5_K_M
d0e9675cf775 • 5.7GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q6_K
576770c27967 • 6.6GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-q8_0
4b48f929dc16 • 8.5GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:8b-v1.5-fp16
54f366e1115a • 16GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5
ab8941f03aa3 • 40GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q2_K
8fde9769839c • 26GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q3_K_S
6c487abb0e1f • 31GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q3_K_M
47d621963e0c • 34GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q3_K_L
d894d5e58d1e • 37GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q4_0
ab8941f03aa3 • 40GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q4_1
ae356afdf521 • 44GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q4_K_S
7d6f62f9c1c6 • 40GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q4_K_M
bd9cc94a71c9 • 43GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q5_0
29f1075baf3a • 49GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q5_1
3adf827c2f0c • 53GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q5_K_S
2650a0fefd9b • 49GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q5_K_M
275a26d672ac • 50GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q6_K
8cc009d2a270 • 58GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-q8_0
1fb999cb1cad • 75GB • 8K context window •
Text input • 1 year ago
llama3-chatqa:70b-v1.5-fp16
d46dd05cde4c • 141GB • 8K context window •
Text input • 1 year ago