github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2026-03-18 11:07:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix https://github.com/hwchase17/langchain/issues/2392 (#2393)

Browse Source 
As noted in
https://github.com/ggerganov/llama.cpp/blob/master/migrate-ggml-2023-03-30-pr613.py,

Authors from `llama.cpp` caused a breaking change to the file format on
2023-03-30 in: https://github.com/ggerganov/llama.cpp/pull/613

Therefore, we need further use `migrate-ggml-2023-03-30-pr613.py` to
convert the llama model.
This commit is contained in:
Shoufa Chen
2023-04-07 05:43:46 +08:00
committed by GitHub
parent bd780a8223
commit 44dfda990b
2 changed files with 13 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tests/integration_tests/embeddings/test_llamacpp.py
View File

@@ -14,17 +14,22 @@ def get_model() -> str:
model_url = "https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml/resolve/main/ggml-alpaca-7b-q4.bin"
tokenizer_url = "https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer.model"
conversion_script = "https://github.com/ggerganov/llama.cpp/raw/master/convert-unversioned-ggml-to-ggml.py"
migrate_script = "https://github.com/ggerganov/llama.cpp/raw/master/migrate-ggml-2023-03-30-pr613.py"
local_filename = model_url.split("/")[-1]
local_filename_ggjt = local_filename.split('.')[0] + '-ggjt.' + local_filename.split('.')[1]
if not os.path.exists("convert-unversioned-ggml-to-ggml.py"):
urlretrieve(conversion_script, "convert-unversioned-ggml-to-ggml.py")
if not os.path.exists("migrate-ggml-2023-03-30-pr613.py"):
urlretrieve(migrate_script, "migrate-ggml-2023-03-30-pr613.py")
if not os.path.exists("tokenizer.model"):
urlretrieve(tokenizer_url, "tokenizer.model")
if not os.path.exists(local_filename):
urlretrieve(model_url, local_filename)
os.system("python convert-unversioned-ggml-to-ggml.py . tokenizer.model")
os.system(f"python convert-unversioned-ggml-to-ggml.py . tokenizer.model")
os.system(f"python migrate-ggml-2023-03-30-pr613.py {local_filename} {local_filename_ggjt}")
return local_filename
return local_filename_ggjt
def test_llamacpp_embedding_documents() -> None:

7
tests/integration_tests/llms/test_llamacpp.py
View File

@@ -13,17 +13,22 @@ def get_model() -> str:
model_url = "https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml/resolve/main/ggml-alpaca-7b-q4.bin"
tokenizer_url = "https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer.model"
conversion_script = "https://github.com/ggerganov/llama.cpp/raw/master/convert-unversioned-ggml-to-ggml.py"
migrate_script = "https://github.com/ggerganov/llama.cpp/raw/master/migrate-ggml-2023-03-30-pr613.py"
local_filename = model_url.split("/")[-1]
local_filename_ggjt = local_filename.split('.')[0] + '-ggjt.' + local_filename.split('.')[1]
if not os.path.exists("convert-unversioned-ggml-to-ggml.py"):
urlretrieve(conversion_script, "convert-unversioned-ggml-to-ggml.py")
if not os.path.exists("migrate-ggml-2023-03-30-pr613.py"):
urlretrieve(migrate_script, "migrate-ggml-2023-03-30-pr613.py")
if not os.path.exists("tokenizer.model"):
urlretrieve(tokenizer_url, "tokenizer.model")
if not os.path.exists(local_filename):
urlretrieve(model_url, local_filename)
os.system(f"python convert-unversioned-ggml-to-ggml.py . tokenizer.model")
os.system(f"python migrate-ggml-2023-03-30-pr613.py {local_filename} {local_filename_ggjt}")
return local_filename
return local_filename_ggjt
def test_llamacpp_inference() -> None: