latest
4.4GB
from mayflowergmbh/DiscoLM_German_7b_v1-laser
7B
189 Pulls Updated 7 months ago
Updated 7 months ago
7 months ago
7ee782956d4a · 4.4GB
model
archllama
·
parameters7.24B
·
quantizationQ4_K_M
4.4GB
params
{"num_ctx":8192,"stop":["<|im_start","<|im_end","|im_start","|im_end"]}
82B
template
{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
156B
Readme
Upload of quantized GGUF of DiscoLM with Layer Selective Rank Reduction (https://github.com/cognitivecomputations/laserRMT) as provided by mayflowergmbh/DiscoLM_German_7b_v1-laser
for experimenting with the model