-
Notifications
You must be signed in to change notification settings - Fork 43.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat(forge/llm): Add LlamafileProvider
#7091
Open
k8si
wants to merge
20
commits into
Significant-Gravitas:master
Choose a base branch
from
Mozilla-Ocho:draft-llamafile-support
base: master
Could not load branches
Branch not found: {{ refName }}
Could not load tags
Nothing to show
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+486
−3
Open
Changes from all commits
Commits
Show all changes
20 commits
Select commit
Hold shift + click to select a range
03d8e1e
Add minimal implementation of LlamafileProvider, a new ChatModelProvi…
k8si ed1dfd0
Adapt model prompt message roles to be compatible with the Mistral-7b…
k8si c56c290
In `OpenAIProvider`, change methods `count_message_tokens`, `count_to…
k8si 234d059
misc cleanup
k8si 05d2b81
add README for llamafile integration including setup instruction + no…
k8si 1cd3e8b
simplify mistral message handling; set seed=0 in chat completion kwar…
k8si dc36c69
set mistral max_tokens to actual value configured in the model and ch…
k8si e426766
Merge branch 'master' into draft-llamafile-support
k8si d63aa23
Merge branch 'master' into draft-llamafile-support
Pwuts 7e7037d
remove llamafile stuff from openai.py
Pwuts 3c1f283
Merge branch 'master' into draft-llamafile-support
Pwuts 5d0f8b0
fix linting errors
Pwuts 960155a
Create `BaseOpenAIProvider` with common functionality from `OpenAIPro…
Pwuts 7aed930
Merge branch 'master' into draft-llamafile-support
Pwuts 02d0691
Merge branch 'master' into draft-llamafile-support
Pwuts f53c2de
move llamafile stuff into folders
Pwuts f78ad94
clean up llamafile readme
Pwuts 1a00ecf
Improve llamafile model name cleaning logic
Pwuts 3c8bf3c
expand setup instructions and info for llamafile
Pwuts 65433ba
combine llamafile setup.sh and serve.sh into single cross-platform se…
Pwuts File filter
Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,2 @@ | ||
*.llamafile | ||
*.llamafile.exe |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,65 @@ | ||
#!/usr/bin/env python3 | ||
""" | ||
Use llamafile to serve a (quantized) mistral-7b-instruct-v0.2 model | ||
|
||
Usage: | ||
cd <repo-root>/autogpt | ||
./scripts/llamafile/serve.py | ||
""" | ||
|
||
import os | ||
import platform | ||
import subprocess | ||
from pathlib import Path | ||
|
||
LLAMAFILE = Path( | ||
"mistral-7b-instruct-v0.2.Q5_K_M.llamafile" | ||
+ (".exe" if platform.system() == "Windows" else "") | ||
) | ||
|
||
|
||
def report_download_progress(chunk_number: int, chunk_size: int, total_size: int): | ||
if total_size != -1: | ||
downloaded_size = chunk_number * chunk_size | ||
percent = min(1, downloaded_size / total_size) | ||
bar = "#" * int(40 * percent) | ||
print( | ||
f"\rDownloading: [{bar:<40}] {percent:.0%}" | ||
f" - {downloaded_size/1e6:.1f}/{total_size/1e6:.1f} MB", | ||
end="", | ||
) | ||
|
||
|
||
def download_llamafile(): | ||
print(f"Downloading {LLAMAFILE.name}...") | ||
import urllib.request | ||
|
||
url = "https://huggingface.co/jartine/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q5_K_M.llamafile" # noqa | ||
|
||
urllib.request.urlretrieve(url, LLAMAFILE.name, reporthook=report_download_progress) | ||
print() | ||
|
||
LLAMAFILE.chmod(0o755) | ||
subprocess.run([LLAMAFILE, "--version"], check=True) | ||
|
||
print( | ||
"\n" | ||
"NOTE: To use other models besides mistral-7b-instruct-v0.2, " | ||
"download them into autogpt/scripts/llamafile/" | ||
) | ||
|
||
|
||
# Go to autogpt/scripts/llamafile/ | ||
os.chdir(Path(__file__).resolve().parent) | ||
|
||
if not LLAMAFILE.is_file(): | ||
download_llamafile() | ||
|
||
subprocess.run( | ||
[LLAMAFILE, "--server", "--nobrowser", "--ctx-size", "0", "--n-predict", "1024"], | ||
check=True, | ||
) | ||
|
||
# note: --ctx-size 0 means the prompt context size will be set directly from the | ||
# underlying model configuration. This may cause slow response times or consume | ||
# a lot of memory. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,36 @@ | ||
# Llamafile Integration Notes | ||
|
||
Tested with: | ||
* Python 3.11 | ||
* Apple M2 Pro (32 GB), macOS 14.2.1 | ||
* quantized mistral-7b-instruct-v0.2 | ||
|
||
## Setup | ||
|
||
Download a `mistral-7b-instruct-v0.2` llamafile: | ||
```shell | ||
wget -nc https://huggingface.co/jartine/Mistral-7B-Instruct-v0.2-llamafile/resolve/main/mistral-7b-instruct-v0.2.Q5_K_M.llamafile | ||
chmod +x mistral-7b-instruct-v0.2.Q5_K_M.llamafile | ||
./mistral-7b-instruct-v0.2.Q5_K_M.llamafile --version | ||
``` | ||
|
||
Run the llamafile server: | ||
```shell | ||
LLAMAFILE="./mistral-7b-instruct-v0.2.Q5_K_M.llamafile" | ||
|
||
"${LLAMAFILE}" \ | ||
--server \ | ||
--nobrowser \ | ||
--ctx-size 0 \ | ||
--n-predict 1024 | ||
|
||
# note: ctx-size=0 means the prompt context size will be set directly from the | ||
# underlying model configuration. This may cause slow response times or consume | ||
# a lot of memory. | ||
``` | ||
|
||
## TODOs | ||
|
||
* `SMART_LLM`/`FAST_LLM` configuration: Currently, the llamafile server only serves one model at a time. However, there's no reason you can't start multiple llamafile servers on different ports. To support using different models for `smart_llm` and `fast_llm`, you could implement config vars like `LLAMAFILE_SMART_LLM_URL` and `LLAMAFILE_FAST_LLM_URL` that point to different llamafile servers (one serving a 'big model' and one serving a 'fast model'). | ||
* Authorization: the `serve.sh` script does not set up any authorization for the llamafile server; this can be turned on by adding arg `--api-key <some-key>` to the server startup command. However I haven't attempted to test whether the integration with autogpt works when this feature is turned on. | ||
* Test with other models |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,17 @@ | ||
from .llamafile import ( | ||
LLAMAFILE_CHAT_MODELS, | ||
LLAMAFILE_EMBEDDING_MODELS, | ||
LlamafileCredentials, | ||
LlamafileModelName, | ||
LlamafileProvider, | ||
LlamafileSettings, | ||
) | ||
|
||
__all__ = [ | ||
"LLAMAFILE_CHAT_MODELS", | ||
"LLAMAFILE_EMBEDDING_MODELS", | ||
"LlamafileCredentials", | ||
"LlamafileModelName", | ||
"LlamafileProvider", | ||
"LlamafileSettings", | ||
] |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If this is just as example then fine but otherwise
LLAMAFILE
could be provided as an argument.