Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit 196650c

Browse filesBrowse files
abetlenabetlen
committed
Update model paths to be more clear they should point to file
1 parent a79d3eb commit 196650c
Copy full SHA for 196650c

File tree

Expand file treeCollapse file tree

8 files changed

+12
-12
lines changed
Filter options
Expand file treeCollapse file tree

8 files changed

+12
-12
lines changed

‎README.md

Copy file name to clipboardExpand all lines: README.md
+3-3Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -27,14 +27,14 @@ pip install llama-cpp-python
2727

2828
```python
2929
>>> from llama_cpp import Llama
30-
>>> llm = Llama(model_path="models/7B/...")
30+
>>> llm = Llama(model_path="./models/7B/ggml-model.bin")
3131
>>> output = llm("Q: Name the planets in the solar system? A: ", max_tokens=32, stop=["Q:", "\n"], echo=True)
3232
>>> print(output)
3333
{
3434
"id": "cmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
3535
"object": "text_completion",
3636
"created": 1679561337,
37-
"model": "models/7B/...",
37+
"model": "./models/7B/ggml-model.bin",
3838
"choices": [
3939
{
4040
"text": "Q: Name the planets in the solar system? A: Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, Neptune and Pluto.",
@@ -60,7 +60,7 @@ To install the server package and get started:
6060

6161
```bash
6262
pip install llama-cpp-python[server]
63-
export MODEL=./models/7B
63+
export MODEL=./models/7B/ggml-model.bin
6464
python3 -m llama_cpp.server
6565
```
6666

‎docs/index.md

Copy file name to clipboardExpand all lines: docs/index.md
+3-3Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -29,14 +29,14 @@ pip install llama-cpp-python
2929

3030
```python
3131
>>> from llama_cpp import Llama
32-
>>> llm = Llama(model_path="models/7B/...")
32+
>>> llm = Llama(model_path="./models/7B/ggml-model.bin")
3333
>>> output = llm("Q: Name the planets in the solar system? A: ", max_tokens=32, stop=["Q:", "\n"], echo=True)
3434
>>> print(output)
3535
{
3636
"id": "cmpl-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
3737
"object": "text_completion",
3838
"created": 1679561337,
39-
"model": "models/7B/...",
39+
"model": "./models/7B/ggml-model.bin",
4040
"choices": [
4141
{
4242
"text": "Q: Name the planets in the solar system? A: Mercury, Venus, Earth, Mars, Jupiter, Saturn, Uranus, Neptune and Pluto.",
@@ -62,7 +62,7 @@ To install the server package and get started:
6262

6363
```bash
6464
pip install llama-cpp-python[server]
65-
export MODEL=./models/7B
65+
export MODEL=./models/7B/ggml-model.bin
6666
python3 -m llama_cpp.server
6767
```
6868

‎examples/high_level_api/fastapi_server.py

Copy file name to clipboardExpand all lines: examples/high_level_api/fastapi_server.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
55
```bash
66
pip install fastapi uvicorn sse-starlette
7-
export MODEL=../models/7B/...
7+
export MODEL=../models/7B/ggml-model.bin
88
uvicorn fastapi_server_chat:app --reload
99
```
1010

‎examples/high_level_api/high_level_api_embedding.py

Copy file name to clipboardExpand all lines: examples/high_level_api/high_level_api_embedding.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
from llama_cpp import Llama
44

55
parser = argparse.ArgumentParser()
6-
parser.add_argument("-m", "--model", type=str, default=".//models/...")
6+
parser.add_argument("-m", "--model", type=str, default="../models/7B/ggml-model.bin")
77
args = parser.parse_args()
88

99
llm = Llama(model_path=args.model, embedding=True)

‎examples/high_level_api/high_level_api_inference.py

Copy file name to clipboardExpand all lines: examples/high_level_api/high_level_api_inference.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
from llama_cpp import Llama
55

66
parser = argparse.ArgumentParser()
7-
parser.add_argument("-m", "--model", type=str, default="./models/...")
7+
parser.add_argument("-m", "--model", type=str, default="../models/7B/ggml-models.bin")
88
args = parser.parse_args()
99

1010
llm = Llama(model_path=args.model)

‎examples/high_level_api/high_level_api_streaming.py

Copy file name to clipboardExpand all lines: examples/high_level_api/high_level_api_streaming.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
from llama_cpp import Llama
55

66
parser = argparse.ArgumentParser()
7-
parser.add_argument("-m", "--model", type=str, default="./models/...")
7+
parser.add_argument("-m", "--model", type=str, default="../models/7B/ggml-models.bin")
88
args = parser.parse_args()
99

1010
llm = Llama(model_path=args.model)

‎examples/high_level_api/langchain_custom_llm.py

Copy file name to clipboardExpand all lines: examples/high_level_api/langchain_custom_llm.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ def _identifying_params(self) -> Mapping[str, Any]:
2929

3030

3131
parser = argparse.ArgumentParser()
32-
parser.add_argument("-m", "--model", type=str, default="./models/...")
32+
parser.add_argument("-m", "--model", type=str, default="../models/7B/ggml-models.bin")
3333
args = parser.parse_args()
3434

3535
# Load the model

‎examples/low_level_api/low_level_api_llama_cpp.py

Copy file name to clipboardExpand all lines: examples/low_level_api/low_level_api_llama_cpp.py
+1-1Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,7 @@
99
prompt = b"\n\n### Instruction:\nWhat is the capital of France?\n\n### Response:\n"
1010

1111
lparams = llama_cpp.llama_context_default_params()
12-
ctx = llama_cpp.llama_init_from_file(b"models/ggml-alpaca-7b-q4.bin", lparams)
12+
ctx = llama_cpp.llama_init_from_file(b"../models/7B/ggml-model.bin", lparams)
1313

1414
# determine the required inference memory per token:
1515
tmp = [0, 1, 2, 3]

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.