CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-10 10:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-08 17:30:49 -04:00
parent fee3c1d740 d4d915d351
commit 6840ac0bca
242 changed files with 83873 additions and 22119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
convert-hf-to-gguf.py
View File

@@ -1,4 +1,5 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from __future__ import annotations
@@ -474,6 +475,9 @@ class Model:
if chkhsh == "c136ed14d01c2745d4f60a9596ae66800e2b61fa45643e72436041855ad4089d":
# ref: https://huggingface.co/abacusai/Smaug-Llama-3-70B-Instruct
res = "smaug-bpe"
if chkhsh == "7967bfa498ade6b757b064f31e964dddbb80f8f9a4d68d4ba7998fcf281c531a":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-code
res = "jina-v2-code"
if res is None:
logger.warning("\n")
@@ -2580,11 +2584,13 @@ class JinaBertV2Model(BertModel):
def get_tensors(self):
for name, data in super().get_tensors():
if 'gated_layers' in name:
if 'gated_layer' in name:
d1 = data[:self.intermediate_size, :]
name1 = name.replace('gated_layers', 'gated_layers_w')
name1 = name1.replace('up_gated_layer', 'gated_layers_v')
d2 = data[self.intermediate_size:, :]
name2 = name.replace('gated_layers', 'gated_layers_v')
name2 = name2.replace('up_gated_layer', 'gated_layers_w')
yield name1, d1
yield name2, d2
continue