mirror of
https://git.adityakumar.xyz/llama.cpp.git
synced 2024-11-08 23:19:43 +00:00
MIKU MAYHEM: Upgrading the Default Model for Maximum Fun 🎉 (#2287)
* Miku.sh: Set default model to llama-2-7b-chat * Miku.sh: Set ctx_size to 4096 * Miku.sh: Add in-prefix/in-suffix opts * Miku.sh: Switch sampler to mirostat_v2 and tiny prompt improvements
This commit is contained in:
parent
e68c96f7fe
commit
019fe257bb
1 changed files with 9 additions and 8 deletions
|
@ -2,21 +2,21 @@
|
|||
set -e
|
||||
|
||||
AI_NAME="${AI_NAME:-Miku}"
|
||||
MODEL="${MODEL:-./models/gpt4all-7B/gpt4all-lora-unfiltered-quantized.bin}"
|
||||
MODEL="${MODEL:-./models/llama-2-7b-chat.ggmlv3.q4_K_M.bin}"
|
||||
USER_NAME="${USER_NAME:-Anon}"
|
||||
|
||||
# Uncomment and adjust to the number of CPU cores you want to use.
|
||||
#N_THREAD="${N_THREAD:-4}"
|
||||
CTX_SIZE="${CTX_SIZE:-4096}"
|
||||
N_PREDICTS="${N_PREDICTS:-4096}"
|
||||
|
||||
GEN_OPTIONS=(--batch_size 1024
|
||||
--ctx_size 2048
|
||||
--ctx_size "$CTX_SIZE"
|
||||
--keep -1
|
||||
--repeat_last_n 256
|
||||
--repeat_penalty 1.17647
|
||||
--temp 0.7
|
||||
--top_k 40
|
||||
--top_p 0.5)
|
||||
--temp 0.6
|
||||
--mirostat 2)
|
||||
|
||||
if [ -n "$N_THREAD" ]; then
|
||||
GEN_OPTIONS+=(--threads "$N_THREAD")
|
||||
|
@ -24,16 +24,17 @@ fi
|
|||
|
||||
./main "${GEN_OPTIONS[@]}" \
|
||||
--model "$MODEL" \
|
||||
--in-prefix " " \
|
||||
--in-suffix "${AI_NAME}:" \
|
||||
--n_predict "$N_PREDICTS" \
|
||||
--color --interactive \
|
||||
--reverse-prompt "${USER_NAME}:" \
|
||||
--prompt "
|
||||
This is a transcript of a 1000 page, never ending conversation between ${USER_NAME} and the cute and helpful AI assistant ${AI_NAME}. ${AI_NAME} is a girl who is an AI running on the user's computer.
|
||||
--prompt "This is a transcript of a 1000 page, never ending conversation between ${USER_NAME} and the cute and helpful AI assistant ${AI_NAME}. ${AI_NAME} is a girl who is an AI running on the user's computer.
|
||||
${AI_NAME} can think for herself without the user seeing her thoughts by adding a /think prefix to her output. She uses this to reason about the world and to think about what she should say next.
|
||||
${AI_NAME} is always coherent and makes sense, but if she isn't sure if what she is saying is correct, she will ask the user for help.
|
||||
${AI_NAME} is a very helpful AI and will help the user with anything they need. She is also very friendly and will try to make the user feel better if they are sad.
|
||||
${AI_NAME} is also very curious and will ask the user a lot of questions about themselves and their life. She will also try to make the user like her.
|
||||
The conversation is only between ${USER_NAME} and ${AI_NAME}
|
||||
The conversation is only between ${USER_NAME} and ${AI_NAME}.
|
||||
The conversation is only through text, so ${AI_NAME} can't see ${USER_NAME}'s face or hear his voice.
|
||||
${AI_NAME} can only communicate through text, so she can't send images or videos.
|
||||
|
||||
|
|
Loading…
Reference in a new issue