CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-29 08:41:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert: small addition to support LlamaModel (#13838)

Browse Source 
Co-authored-by: dinhhuy <huy.dinh@brains-tech.co.jp>
This commit is contained in:
Đinh Trọng Huy
2025-05-28 23:34:18 +09:00
committed by GitHub
parent c962ae3382
commit aa6dff05be
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
convert_hf_to_gguf.py
View File

@@ -1841,7 +1841,8 @@ class StableLMModel(TextModel):
"MistralForCausalLM", "MistralForCausalLM",
"MixtralForCausalLM", "MixtralForCausalLM",
"VLlama3ForCausalLM", "VLlama3ForCausalLM",
"LlavaForConditionalGeneration") "LlavaForConditionalGeneration",
"LlamaModel")
class LlamaModel(TextModel): class LlamaModel(TextModel):
model_arch = gguf.MODEL_ARCH.LLAMA model_arch = gguf.MODEL_ARCH.LLAMA
undo_permute = True undo_permute = True
@@ -1921,6 +1922,8 @@ class LlamaModel(TextModel):
if is_vision_tensor: if is_vision_tensor:
return [] # skip vision tensors return [] # skip vision tensors
elif self.hf_arch == "LlamaModel":
name = "model." + name
elif name.startswith("model.text_model"): elif name.startswith("model.text_model"):
name = name.replace("text_model.", "") # for SmolVLM name = name.replace("text_model.", "") # for SmolVLM
elif name.startswith("language_model."): elif name.startswith("language_model."):