Text Generation
GGUF
English
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
bfloat16
rp
role play
horror
llama2
mergekit
Inference Endpoints
Update README.md
Browse files
README.md
CHANGED
@@ -79,6 +79,10 @@ Note that temp AND "rep pen" changes will drastically change the output ; adjust
|
|
79 |
Also, this model may perform better cold for some prompts: Unload the model, load the model -> prompt it ... rather than
|
80 |
keeping the model loaded at all times.
|
81 |
|
|
|
|
|
|
|
|
|
82 |
<B>Model Template:</B>
|
83 |
|
84 |
This is a LLAMA2 model, and requires Alpaca or Llama2 template, but may work with other template(s) and has maximum context of 4k / 4096.
|
|
|
79 |
Also, this model may perform better cold for some prompts: Unload the model, load the model -> prompt it ... rather than
|
80 |
keeping the model loaded at all times.
|
81 |
|
82 |
+
Recommend using the larger quant you can "run" for quality.
|
83 |
+
|
84 |
+
This repo also has the new "arm quants" : Q4_0_4_4, Q4_0_4_8 and Q4_0_8_8
|
85 |
+
|
86 |
<B>Model Template:</B>
|
87 |
|
88 |
This is a LLAMA2 model, and requires Alpaca or Llama2 template, but may work with other template(s) and has maximum context of 4k / 4096.
|