mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
e6f291d158
* server : fix context shift + simplify self-extend * server : take system_tokens into account * server : more n_past fixes * server : rever n_past_se changes
81 lines
1.9 KiB
Bash
Executable File
81 lines
1.9 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
API_URL="${API_URL:-http://127.0.0.1:8080}"
|
|
|
|
CHAT=(
|
|
"Hello, Assistant."
|
|
"Hello. How may I help you today?"
|
|
"Please tell me the largest city in Europe."
|
|
"Sure. The largest city in Europe is Moscow, the capital of Russia."
|
|
)
|
|
|
|
INSTRUCTION="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions."
|
|
|
|
trim() {
|
|
shopt -s extglob
|
|
set -- "${1##+([[:space:]])}"
|
|
printf "%s" "${1%%+([[:space:]])}"
|
|
}
|
|
|
|
trim_trailing() {
|
|
shopt -s extglob
|
|
printf "%s" "${1%%+([[:space:]])}"
|
|
}
|
|
|
|
format_prompt() {
|
|
echo -n "${INSTRUCTION}"
|
|
printf "\n### Human: %s\n### Assistant: %s" "${CHAT[@]}" "$1"
|
|
}
|
|
|
|
tokenize() {
|
|
curl \
|
|
--silent \
|
|
--request POST \
|
|
--url "${API_URL}/tokenize" \
|
|
--header "Content-Type: application/json" \
|
|
--data-raw "$(jq -ns --arg content "$1" '{content:$content}')" \
|
|
| jq '.tokens[]'
|
|
}
|
|
|
|
N_KEEP=$(tokenize "${INSTRUCTION}" | wc -l)
|
|
|
|
chat_completion() {
|
|
PROMPT="$(trim_trailing "$(format_prompt "$1")")"
|
|
DATA="$(echo -n "$PROMPT" | jq -Rs --argjson n_keep $N_KEEP '{
|
|
prompt: .,
|
|
temperature: 0.2,
|
|
top_k: 40,
|
|
top_p: 0.9,
|
|
n_keep: $n_keep,
|
|
n_predict: 256,
|
|
cache_prompt: true,
|
|
stop: ["\n### Human:"],
|
|
stream: true
|
|
}')"
|
|
|
|
ANSWER=''
|
|
|
|
while IFS= read -r LINE; do
|
|
if [[ $LINE = data:* ]]; then
|
|
CONTENT="$(echo "${LINE:5}" | jq -r '.content')"
|
|
printf "%s" "${CONTENT}"
|
|
ANSWER+="${CONTENT}"
|
|
fi
|
|
done < <(curl \
|
|
--silent \
|
|
--no-buffer \
|
|
--request POST \
|
|
--url "${API_URL}/completion" \
|
|
--header "Content-Type: application/json" \
|
|
--data-raw "${DATA}")
|
|
|
|
printf "\n"
|
|
|
|
CHAT+=("$1" "$(trim "$ANSWER")")
|
|
}
|
|
|
|
while true; do
|
|
read -r -e -p "> " QUESTION
|
|
chat_completion "${QUESTION}"
|
|
done
|