tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-01 06:59:13 -04:00
Code Issues Packages Projects Releases Wiki Activity

model : support LiquidAI LFM2 hybrid family (#14620)

Browse Source 
**Important**
LFM2 was [merged ](https://github.com/huggingface/transformers/pull/39340)into transformers, but has not yet been released.
To convert into gguf, install transformers from source
```shell
pip install "transformers @ git+https://github.com/huggingface/transformers.git@main"
```
This commit is contained in:
Tarek Dakhran
2025-07-11 20:27:01 +02:00
committed by GitHub
parent 756aa1020a
commit f5e96b368f
14 changed files with 373 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-vocab.cpp
View File

@@ -1525,7 +1525,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
tokenizer_pre == "falcon3" ||
tokenizer_pre == "falcon-h1" ||
tokenizer_pre == "pixtral" ||
tokenizer_pre == "midm-2.0") {
tokenizer_pre == "midm-2.0" ||
tokenizer_pre == "lfm2") {
pre_type = LLAMA_VOCAB_PRE_TYPE_LLAMA3;
ignore_merges = true;
add_bos = true;