Skip to content

Add Falcon3 support #10862

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

Add Falcon3 support #10862

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
bf01b18
Add Falcon3 support
mokeddembillel Dec 5, 2024
5d31c23
Use llama vocab
mokeddembillel Dec 10, 2024
f5f3fca
Add chat template
mokeddembillel Dec 10, 2024
d349f61
Change model name
mokeddembillel Dec 16, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions convert_hf_to_gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -525,6 +525,9 @@ def get_vocab_base(self) -> tuple[list[str], list[int], str]:
else:
token: str = reverse_vocab[i]
if token in added_vocab:
# We need to manually encode and decode the added tokens in case special characters
# used for `\n` / `\t` have been manually added in the added tokens
token = tokenizer.decode(tokenizer.encode(token))
if tokenizer.added_tokens_decoder[i].special or self.does_token_look_special(token):
toktypes.append(gguf.TokenType.CONTROL)
else:
Expand Down Expand Up @@ -571,6 +574,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
if chkhsh == "8aeee3860c56296a157a1fe2fad249ec40aa59b1bb5709f4ade11c4e6fe652ed":
# ref: https://huggingface.co/tiiuae/falcon-7b
res = "falcon"
if chkhsh == "9d032fcbd5501f4a38150912590928bfb36091efb5df11b8e2124b0390e3fb1e":
# ref: https://huggingface.co/tiiuae/Falcon3-7B-Base
res = "falcon3"
if chkhsh == "0876d13b50744004aa9aeae05e7b0647eac9d801b5ba4668afc01e709c15e19f":
# ref: https://huggingface.co/BAAI/bge-small-en-v1.5
res = "bert-bge"
Expand Down
1 change: 1 addition & 0 deletions convert_hf_to_gguf_update.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,7 @@ class TOKENIZER_TYPE(IntEnum):
{"name": "deepseek-llm", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-llm-7b-base", },
{"name": "deepseek-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base", },
{"name": "falcon", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/falcon-7b", },
{"name": "falcon3", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/tiiuae/Falcon3-7B-Base", },
{"name": "bert-bge", "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/BAAI/bge-small-en-v1.5", },
{"name": "bert-bge-large", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/BAAI/bge-large-zh-v1.5", },
{"name": "mpt", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mosaicml/mpt-7b", },
Expand Down
14 changes: 14 additions & 0 deletions src/llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6226,6 +6226,11 @@ static void llm_load_vocab(
} else if (
tokenizer_pre == "falcon") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_FALCON;
} else if (
tokenizer_pre == "falcon3") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_LLAMA3;
vocab.tokenizer_ignore_merges = true;
vocab.tokenizer_add_bos = true;
} else if (
tokenizer_pre == "mpt") {
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_MPT;
Expand Down Expand Up @@ -21594,6 +21599,15 @@ static int32_t llama_chat_apply_template_internal(
if (add_ass) {
ss << "<|assistant|>\n";
}
} else if (tmpl == "falcon3" || (tmpl_contains("<|assistant|>") && tmpl_contains("<|user|>"))) {
// Falcon 3
for (auto message : chat) {
std::string role(message->role);
ss << "<|" << role << "|>\n" << message->content << "\n";
}
if (add_ass) {
ss << "<|assistant|>\n";
}
} else if (tmpl == "zephyr" || tmpl_contains("<|user|>")) {
// zephyr template
for (auto message : chat) {
Expand Down
Loading