vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

address comments

Browse source
This commit is contained in:
jmorganca 2024-07-26 15:10:49 -07:00
parent 1a3a1b6d54
commit 90fd87df41
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
convert_hf_to_gguf.py
View file

@ -1583,6 +1583,7 @@ class LlamaModel(Model):
low_freq_wavelen = old_context_len / low_freq_factor
high_freq_wavelen = old_context_len / high_freq_factor
assert low_freq_wavelen != high_freq_wavelen
rope_factors = []
for freq in freqs:
@ -1592,11 +1593,10 @@ class LlamaModel(Model):
elif wavelen > low_freq_wavelen:
rope_factors.append(factor)
else:
assert low_freq_wavelen != high_freq_wavelen
smooth = (old_context_len / wavelen - low_freq_factor) / (high_freq_factor - low_freq_factor)
rope_factors.append(1 / ((1 - smooth) / factor + smooth))
self.gguf_writer.add_tensor(gguf.TENSOR_NAMES[gguf.MODEL_TENSOR.ROPE_FREQS] + ".weight", np.array(rope_factors, dtype=np.float32))
self.gguf_writer.add_tensor(self.format_tensor_name(gguf.MODEL_TENSOR.ROPE_FREQS), np.array(rope_factors, dtype=np.float32))
super().prepare_tensors()