root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-11-13 14:29:52 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Rwkv chat template fix (#10001)

Browse Source 
* llama: remove useless template matching for rwkv-world

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* converter: Add comment about the hack for rwkv models

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Update src/llama.cpp

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Molly Sophia 2024-10-22 21:22:26 +08:00 committed by GitHub
parent c421ac072d
commit 11d47057a5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
convert_hf_to_gguf.py
View File

@ -2865,6 +2865,7 @@ class Rwkv6Model(Model):
self.gguf_writer.add_token_types(toktypes)
special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=False)
special_vocab.chat_template = "rwkv-world"
# hack: Add '\n\n' as the EOT token to make it chat normally
special_vocab._set_special_token("eot", 261)
special_vocab.add_to_gguf(self.gguf_writer)

3
src/llama.cpp
View File

@ -21697,7 +21697,8 @@ static int32_t llama_chat_apply_template_internal(
if (add_ass) {
ss << "[|assistant|]";
}
} else if (tmpl == "rwkv-world" || tmpl_contains("rwkv-world") || tmpl_contains("'User: ' + message['content'] + '\n\nAssistant:'")) {
} else if (tmpl == "rwkv-world" || tmpl_contains("rwkv-world")) {
// this template requires the model to have "\n\n" as EOT token
for (auto message : chat) {
std::string role(message->role);
if (role == "user") {

4
tests/test-chat-template.cpp
View File

@ -65,8 +65,6 @@ int main(void) {
u8"{% for message in messages %}{% if message['role'] == 'user' %}{{'<用户>' + message['content'].strip() + '<AI>'}}{% else %}{{message['content'].strip()}}{% endif %}{% endfor %}",
// DeepSeek-V2
"{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
// RWKV-World
"{% for message in messages %}{% if message['role'] == 'user' %}{{'User: ' + message['content'] + '\n\nAssistant:'}}{% else %}{{message['content'] + '\n\n'}}{% endif %}{% endfor %}",
};
std::vector<std::string> expected_output = {
// teknium/OpenHermes-2.5-Mistral-7B
@ -111,8 +109,6 @@ int main(void) {
u8"You are a helpful assistant<用户>Hello<AI>Hi there<用户>Who are you<AI>I am an assistant<用户>Another question<AI>",
// DeepSeek-V2
u8"You are a helpful assistant\n\nUser: Hello\n\nAssistant: Hi there<｜end▁of▁sentence｜>User: Who are you\n\nAssistant: I am an assistant <｜end▁of▁sentence｜>User: Another question\n\nAssistant:",
// RWKV-World
"You are a helpful assistant\n\nUser: Hello\n\nAssistant:Hi there\n\nUser: Who are you\n\nAssistant: I am an assistant \n\nUser: Another question\n\nAssistant:",
};
std::vector<char> formatted_chat(1024);
int32_t res;