File tree Expand file tree Collapse file tree 2 files changed +44
-3
lines changed Expand file tree Collapse file tree 2 files changed +44
-3
lines changed Original file line number Diff line number Diff line change
1
+ #! /bin/bash
2
+
3
+ set -e
4
+
5
+ cd " $( dirname " $0 " ) /.." || exit
6
+
7
+ MODEL=" ${MODEL:- ./ models/ ggml-vic13b-uncensored-q5_0.bin} "
8
+ PROMPT_TEMPLATE=${PROMPT_TEMPLATE:- ./ prompts/ chat.txt}
9
+ USER_NAME=" ### Human"
10
+ AI_NAME=" ### Assistant"
11
+
12
+ # Adjust to the number of CPU cores you want to use.
13
+ N_THREAD=" ${N_THREAD:- 8} "
14
+ # Number of tokens to predict (made it larger than default because we want a long interaction)
15
+ N_PREDICTS=" ${N_PREDICTS:- 2048} "
16
+
17
+ # Note: you can also override the generation options by specifying them on the command line:
18
+ # For example, override the context size by doing: ./chatLLaMa --ctx_size 1024
19
+ GEN_OPTIONS=" ${GEN_OPTIONS:- --ctx_size 2048 --temp 0.7 --top_k 40 --top_p 0.5 --repeat_last_n 256 --batch_size 1024 --repeat_penalty 1.17647} "
20
+
21
+ DATE_TIME=$( date +%H:%M)
22
+ DATE_YEAR=$( date +%Y)
23
+
24
+ PROMPT_FILE=$( mktemp -t llamacpp_prompt.XXXXXXX.txt)
25
+
26
+ sed -e " s/\[\[USER_NAME\]\]/$USER_NAME /g" \
27
+ -e " s/\[\[AI_NAME\]\]/$AI_NAME /g" \
28
+ -e " s/\[\[DATE_TIME\]\]/$DATE_TIME /g" \
29
+ -e " s/\[\[DATE_YEAR\]\]/$DATE_YEAR /g" \
30
+ $PROMPT_TEMPLATE > $PROMPT_FILE
31
+
32
+ # shellcheck disable=SC2086 # Intended splitting of GEN_OPTIONS
33
+ ./bin/main $GEN_OPTIONS \
34
+ --model " $MODEL " \
35
+ --threads " $N_THREAD " \
36
+ --n_predict " $N_PREDICTS " \
37
+ --color --interactive \
38
+ --file ${PROMPT_FILE} \
39
+ --reverse-prompt " ### Human:" \
40
+ --in-prefix ' ' \
41
+ " $@ "
Original file line number Diff line number Diff line change @@ -244,9 +244,9 @@ extern "C" {
244
244
LLAMA_API const char * llama_token_to_str (const struct llama_context * ctx, llama_token token);
245
245
246
246
// Special tokens
247
- LLAMA_API llama_token llama_token_bos ();
248
- LLAMA_API llama_token llama_token_eos ();
249
- LLAMA_API llama_token llama_token_nl ();
247
+ LLAMA_API llama_token llama_token_bos (); // beginning-of-sentence
248
+ LLAMA_API llama_token llama_token_eos (); // end-of-sentence
249
+ LLAMA_API llama_token llama_token_nl (); // next-line
250
250
251
251
// Sampling functions
252
252
You can’t perform that action at this time.
0 commit comments