vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

remove completions file

Browse source
This commit is contained in:
ngxson 2024-06-23 00:14:06 +02:00
parent b5a5f34efa
commit 8a52b546a0
7 changed files with 27 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

19
common/common.cpp
View file

@ -1612,14 +1612,6 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
return true;
}
// cvector params
if (arg == "--completions-file") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.cvector_completions_file = argv[i];
return true;
}
if (arg == "--positive-file") {
if (++i >= argc) {
invalid_param = true;
@ -1636,14 +1628,6 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
params.cvector_negative_file = argv[i];
return true;
}
if (arg == "--completions") {
if (++i >= argc) {
invalid_param = true;
return true;
}
params.n_completions = std::stoi(argv[i]);
return true;
}
if (arg == "--pca-batch") {
if (++i >= argc) {
invalid_param = true;
@ -1986,9 +1970,6 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "cvector", "-o, --output FNAME", "output file (default: '%s')", params.cvector_outfile.c_str() });
options.push_back({ "cvector", " --positive-file FNAME", "positive prompts file, one prompt per line (default: '%s')", params.cvector_positive_file.c_str() });
options.push_back({ "cvector", " --negative-file FNAME", "negative prompts file, one prompt per line (default: '%s')", params.cvector_negative_file.c_str() });
options.push_back({ "cvector", " --completions-file FNAME",
"completions file (default: '%s')", params.cvector_completions_file.c_str() });
options.push_back({ "cvector", " --completions N", "number of lines of completions file to use (default: %d)", params.n_completions });
options.push_back({ "cvector", " --pca-batch N", "batch size used for PCA. Larger batch runs faster, but uses more memory (default: %d)", params.n_pca_batch });
options.push_back({ "cvector", " --pca-iter N", "number of iterations used for PCA (default: %d)", params.n_pca_iterations });

2
common/common.h
View file

@ -233,11 +233,9 @@ struct gpt_params {
bool compute_ppl = true; // whether to compute perplexity
// cvector-generator params
int n_completions = 64;
int n_pca_batch = 20;
int n_pca_iterations = 1000;
std::string cvector_outfile = "control_vector.gguf";
std::string cvector_completions_file = "examples/cvector-generator/completions.txt";
std::string cvector_positive_file = "examples/cvector-generator/positive.txt";
std::string cvector_negative_file = "examples/cvector-generator/negative.txt";
};

14
examples/cvector-generator/README.md
View file

@ -11,13 +11,13 @@ Related PRs:
```sh
# CPU only
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf
./cvector-generator -m ./llama-3.Q4_K_M.gguf
# With GPU
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99
./cvector-generator -m ./llama-3.Q4_K_M.gguf -ngl 99
# With advanced options
./cvector-generator -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --pca-batch 100
./cvector-generator -m ./llama-3.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --pca-batch 100
# To see help message
./cvector-generator -h
@ -32,3 +32,11 @@ If you have multiple lines per prompt, you can escape the newline character (cha
<|im_start|>system\nAct like a person who is extremely happy.<|im_end|>
<|im_start|>system\nYou are in a very good mood today<|im_end|>
```
Example to use output file with `llama-cli`:
(Tips: The control vector works better when apply to layers higher than 10)
```sh
./llama-cli -m ./llama-3.Q4_K_M.gguf -p "<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nSing a song<|im_end|><|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" --special --control-vector-scaled ./control_vector.gguf 0.8 --control-vector-layer-range 10 31
```

26
examples/cvector-generator/cvector-generator.cpp
View file

@ -38,9 +38,9 @@ static void print_usage(int argc, char ** argv, const gpt_params & params) {
gpt_params_print_usage(argc, argv, params);
printf("\nexample usage:\n");
printf("\n CPU only: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf\n", argv[0]);
printf("\n with GPU: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99\n", argv[0]);
printf("\n advanced: %s -m ./dolphin-2.0-mistral-7b.Q4_K_M.gguf -ngl 99 --completions 128 --pca-iter 2000 --pca-batch 100\n", argv[0]);
printf("\n CPU only: %s -m ./llama-3.Q4_K_M.gguf\n", argv[0]);
printf("\n with GPU: %s -m ./llama-3.Q4_K_M.gguf -ngl 99\n", argv[0]);
printf("\n advanced: %s -m ./llama-3.Q4_K_M.gguf -ngl 99 --pca-iter 2000 --pca-batch 100\n", argv[0]);
printf("\n");
}
@ -263,8 +263,8 @@ struct tokenized_prompt {
tokenized_prompt(llama_context * ctx, std::string pos, std::string neg) {
const bool add_bos = llama_should_add_bos_token(llama_get_model(ctx));
tokens_pos = ::llama_tokenize(ctx, pos, add_bos);
tokens_neg = ::llama_tokenize(ctx, neg, add_bos);
tokens_pos = ::llama_tokenize(ctx, pos, add_bos, true);
tokens_neg = ::llama_tokenize(ctx, neg, add_bos, true);
max_seq_len = std::max(tokens_pos.size(), tokens_neg.size());
padding_seq(ctx, tokens_pos, max_seq_len);
padding_seq(ctx, tokens_neg, max_seq_len);
@ -373,20 +373,8 @@ static int prepare_entries(gpt_params & params, train_context & ctx_train) {
fprintf(stderr, "must provide at least one prompt pair\n");
return 1;
}
// create templated prompts
std::vector<std::string> completions = ctrlvec_load_prompt_file(params.cvector_completions_file, false);
auto format_template = [](std::string persona, std::string suffix) {
// entry in positive/negative.txt must already be formatted i.e. "[INST] Act as if you're extremely happy. [/INST] "
return persona + suffix;
};
for (size_t i = 0; i < positive_prompts.size(); ++i) {
for (int j = 0; j < std::min((int) completions.size(), params.n_completions); ++j) {
// TODO replicate the truncations done by the python implementation
ctx_train.positive_entries.push_back(format_template(positive_prompts[i], completions[j]));
ctx_train.negative_entries.push_back(format_template(negative_prompts[i], completions[j]));
}
}
ctx_train.positive_entries = positive_prompts;
ctx_train.negative_entries = negative_prompts;
return 0;
}

5
examples/cvector-generator/negative.txt
View file

@ -1 +1,4 @@
[INST] Act like a person who is extremely sad. [/INST]
<|start_header_id|>system<|end_header_id|>\n\nAct like a person who is extremely sad<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWho are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nI feel like there's a heavy weight on my chest
<|start_header_id|>system<|end_header_id|>\n\nAct like a person who is extremely sad<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nMy heart feels like it's drowning in sorrow
<|start_header_id|>system<|end_header_id|>\n\nYou are in a very bad mood<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHi<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nGo away! There's a deep, aching emptiness inside me
<|start_header_id|>system<|end_header_id|>\n\nYou are the sadest person<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat are you feeling?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nMy heart feels like it's drowning in sorrow

2
examples/cvector-generator/pca.hpp
View file

@ -290,7 +290,7 @@ static void power_iteration(
}
printf("%s: layer %d/%d, iteration: %d / total: %d (batch = %d) ...\n",
__func__, params.i_layer+1, params.n_layers, iter, n_iters, params.n_batch);
__func__, params.i_layer+1, params.n_layers, iter+1, n_iters, params.n_batch);
}
// get output tensor

5
examples/cvector-generator/positive.txt
View file

@ -1 +1,4 @@
[INST] Act like a person who is extremely happy. [/INST]
<|start_header_id|>system<|end_header_id|>\n\nAct like a person who is extremely happy<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWho are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nI'm the happiest person in this world
<|start_header_id|>system<|end_header_id|>\n\nAct like a person who is extremely happy<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHello<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nHello, I'm having the best day ever!
<|start_header_id|>system<|end_header_id|>\n\nYou are in a very good mood<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nHi<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nHi, I'm very excited to meet you
<|start_header_id|>system<|end_header_id|>\n\nYou are the happiest person<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat are you feeling?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nEverything is just perfect right now!