examples : server chat mode with llama2 (#2400)

* add: server chat mode with llama2

* fix: remove the unnecessary last \n
This commit is contained in:
nhamanasu 2023-07-29 03:02:10 +09:00 committed by GitHub
parent d91f3f0c55
commit 34ae1caf7f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 135 additions and 0 deletions

View File

@ -0,0 +1,26 @@
#!/bin/bash
set -e
cd "$(dirname "$0")/.." || exit
# Specify the model you want to use here:
MODEL="${MODEL:-./models/llama-2-13b-chat.ggmlv3.q5_K_M.bin}"
PROMPT_TEMPLATE=${PROMPT_TEMPLATE:-./prompts/chat-system.txt}
# Adjust to the number of CPU cores you want to use.
N_THREAD="${N_THREAD:-12}"
# Note: you can also override the generation options by specifying them on the command line:
GEN_OPTIONS="${GEN_OPTIONS:---ctx_size 4096 --batch-size 1024}"
# shellcheck disable=SC2086 # Intended splitting of GEN_OPTIONS
./server $GEN_OPTIONS \
--model "$MODEL" \
--threads "$N_THREAD" \
--rope-freq-scale 1.0 \
"$@"
# I used this to test the model with mps, but omitted it from the general purpose. If you want to use it, just specify it on the command line.
# -ngl 1 \

View File

@ -0,0 +1,109 @@
#!/bin/bash
API_URL="${API_URL:-http://127.0.0.1:8080}"
CHAT=(
"Hello, Assistant."
"Hello. How may I help you today?"
)
INSTRUCTION="A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions."
trim() {
shopt -s extglob
set -- "${1##+([[:space:]])}"
printf "%s" "${1%%+([[:space:]])}"
}
trim_trailing() {
shopt -s extglob
printf "%s" "${1%%+([[:space:]])}"
}
format_prompt() {
if [[ "${#CHAT[@]}" -eq 0 ]]; then
echo -n "[INST] <<SYS>>\n${INSTRUCTION}\n<</SYS>>"
else
LAST_INDEX=$(( ${#CHAT[@]} - 1 ))
echo -n "${CHAT[$LAST_INDEX]}\n[INST] $1 [/INST]"
fi
}
tokenize() {
curl \
--silent \
--request POST \
--url "${API_URL}/tokenize" \
--header "Content-Type: application/json" \
--data-raw "$(jq -ns --arg content "$1" '{content:$content}')" \
| jq '.tokens[]'
}
N_KEEP=$(tokenize "[INST] <<SYS>>\n${INSTRUCTION}\n<</SYS>>" | 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: $n_keep,
n_predict: 1024,
stop: ["[INST]"],
stream: true
}')"
# Create a temporary file to hold the Python output
TEMPFILE=$(mktemp)
exec 3< <(curl \
--silent \
--no-buffer \
--request POST \
--url "${API_URL}/completion" \
--header "Content-Type: application/json" \
--data-raw "${DATA}")
python -c "
import json
import sys
answer = ''
while True:
line = sys.stdin.readline()
if not line:
break
if line.startswith('data: '):
json_content = line[6:].strip()
content = json.loads(json_content)['content']
sys.stdout.write(content)
sys.stdout.flush()
answer += content
answer = answer.rstrip('\n')
# Write the answer to the temporary file
with open('$TEMPFILE', 'w') as f:
f.write(answer)
" <&3
exec 3<&-
# Read the answer from the temporary file
ANSWER=$(cat $TEMPFILE)
# Clean up the temporary file
rm $TEMPFILE
printf "\n"
CHAT+=("$1" "$(trim "$ANSWER")")
}
while true; do
echo -en "\033[0;32m" # Green color
read -r -e -p "> " QUESTION
echo -en "\033[0m" # Reset color
chat_completion "${QUESTION}"
done