from mayflowergmbh/DiscoLM_German_7b_v1-laser
286 Pulls Updated 14 months ago
Updated 14 months ago
14 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",
82B
template
{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
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