TheBloke
/

Llama-2-70B-Chat-GGML

Text Generation

Model card Files Files and versions Community

Resources

View closed (1)

AttributeError: 'Message' object has no attribute 'replace'

#16 opened about 1 year ago by

Unzip problem

#15 opened about 1 year ago by

Looking for GGUF format for this model

#14 opened over 1 year ago by

to add new command line parameter -gqa 8

#13 opened over 1 year ago by

Unable to convert `llama-2-70b-chat.ggmlv3.q4_K_M.bin` to GGUF

#12 opened over 1 year ago by

Unable to Load model TheBloke/Llama-2-70B-Chat-GGML . Name : llama-2-70b-chat.ggmlv3.q5_0.bin

#11 opened over 1 year ago by

How to start the 70b Server Version?

#10 opened over 1 year ago by

Has anyone been able to use GPU and CPU more fully for higher speed output?

#9 opened over 1 year ago by

Seeking affordable GPU recommendations for the 70B 8-bit quantization

#8 opened over 1 year ago by

Cannot write to './llama.cpp/models/llama-2-70b-chat.ggmlv3.q2_K.bin'

#7 opened over 1 year ago by

Unable to load model in latest llama.cpp build

#6 opened over 1 year ago by

prompt brackets issue

#4 opened over 1 year ago by

Chat with documents using llama-2

#3 opened over 1 year ago by

using oobaboga to load model fail for 70b chat ggml Q2_k anad Q3_K_S

#2 opened over 1 year ago by

70B Llama is smarter than Llama 65B

#1 opened over 1 year ago by