tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 20:45:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix errors in conversion.

Browse Source
This commit is contained in:
Vaibhavs10
2025-06-17 16:01:53 +02:00
parent 32ea9c5fc1
commit 02ff085071
2 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
convert_hf_to_gguf.py
View File

@ -6305,8 +6305,11 @@ class SmolLM3Model(LlamaModel):
def set_gguf_parameters(self): def set_gguf_parameters(self):
super().set_gguf_parameters() super().set_gguf_parameters()
if self.model.config.no_rope_layers is not None: # if self.model.config.no_rope_layers is not None:
self.gguf_writer.add_array("smollm3.no_rope_layers", self.model.config.no_rope_layers, gguf.GGUFValueType.INT32) # self.gguf_writer.add_array("smollm3.no_rope_layers", self.model.config.no_rope_layers, gguf.GGUFValueType.INT32)
no_rope_layers = self.hparams.get("no_rope_layers")
if no_rope_layers is not None:
self.gguf_writer.add_array("smollm3.no_rope_layers", no_rope_layers)
###### CONVERSION LOGIC ###### ###### CONVERSION LOGIC ######

1
gguf-py/gguf/constants.py
View File

@ -2114,6 +2114,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
MODEL_TENSOR.ATTN_V, MODEL_TENSOR.ATTN_V,
MODEL_TENSOR.ATTN_OUT, MODEL_TENSOR.ATTN_OUT,
MODEL_TENSOR.ATTN_ROT_EMBD, MODEL_TENSOR.ATTN_ROT_EMBD,
MODEL_TENSOR.FFN_NORM,
MODEL_TENSOR.FFN_GATE, MODEL_TENSOR.FFN_GATE,
MODEL_TENSOR.FFN_DOWN, MODEL_TENSOR.FFN_DOWN,
MODEL_TENSOR.FFN_UP, MODEL_TENSOR.FFN_UP,