Test New LLMs (Llama2, CodeLlama, etc.) on Aider? #1
Conversation
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
…d to account for the prices in `Model` being per 1k tokens.
# Aider chat conversation:
USER: the prices in `Model` are per 1k tokens
ASSISTANT: I see, the prices in the `Model` class are per 1k tokens. Therefore, we need to adjust the calculation of the cost in the `cmd_tokens` method in the `Commands` class in the `aider/commands.py` file.
We will divide the `completion_price` by 1000 before multiplying it with the token count to get the cost.
Here are the changes:
<source>python
aider/commands.py
<<<<<<< ORIGINAL
total = 0
total_cost = 0.0
for tk, msg, tip in res:
total += tk
cost = tk * self.coder.main_model.completion_price
total_cost += cost
msg = msg.ljust(col_width)
self.io.tool_output(f"{fmt(tk)} {msg} {tip} (cost: ${cost:.2f})")
self.io.tool_output("=" * width)
self.io.tool_output(f"{fmt(total)} tokens total (cost: ${total_cost:.2f})")
=======
total = 0
total_cost = 0.0
for tk, msg, tip in res:
total += tk
cost = tk * (self.coder.main_model.completion_price / 1000)
total_cost += cost
msg = msg.ljust(col_width)
self.io.tool_output(f"{fmt(tk)} {msg} {tip} (cost: ${cost:.2f})")
self.io.tool_output("=" * width)
self.io.tool_output(f"{fmt(total)} tokens total (cost: ${total_cost:.2f})")
>>>>>>> UPDATED
</source>
Automatically summarize earlier parts of the chat history
Openrouter compatibility
…is` instead of `==` in `aider/history.py`, `aider/models/__init__.py`, and `aider/models/openrouter.py`.
# Aider chat conversation:
USER: I ran this command:
pre-commit run --all-files
And got this output:
isort....................................................................Passed
black....................................................................Passed
flake8...................................................................Failed
- hook id: flake8
- exit code: 1
aider/history.py:4:1: F401 'tiktoken' imported but unused
import tiktoken
^
aider/models/__init__.py:2:1: F401 '.openai.OpenAIModel' imported but unused
from .openai import OpenAIModel
^
aider/models/__init__.py:3:1: F401 '.openrouter.OpenRouterModel' imported but unused
from .openrouter import OpenRouterModel
^
aider/models/openrouter.py:26:33: E711 comparison to None should be 'if cond is None:'
if cached_model_details == None:
^
ASSISTANT: It seems like there are some unused imports and a comparison to None that is not following the Pythonic way. To fix these issues, we need to modify the following files:
1. `aider/history.py`
2. `aider/models/__init__.py`
3. `aider/models/openrouter.py`
Please add these files to the chat so I can propose the necessary changes.
USER: I added these *read-write* files: aider/history.py, aider/models/openrouter.py, aider/models/__init__.py
ASSISTANT: Great! Now, let's make the necessary changes to these files.
First, in `aider/history.py`, we need to remove the unused import `tiktoken`.
```python
aider/history.py
<<<<<<< HEAD
import tiktoken
=======
>>>>>>> updated
```
Next, in `aider/models/__init__.py`, we need to remove the unused imports `OpenAIModel` and `OpenRouterModel`.
```python
aider/models/__init__.py
<<<<<<< HEAD
from .openai import OpenAIModel
from .openrouter import OpenRouterModel
=======
>>>>>>> updated
```
Finally, in `aider/models/openrouter.py`, we need to change the comparison to None to use `is` instead of `==`.
```python
aider/models/openrouter.py
<<<<<<< HEAD
if cached_model_details == None:
=======
if cached_model_details is None:
>>>>>>> updated
```
These changes should resolve the issues reported by the `flake8` linter.
…usage only show token costs if usage exists
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Hi @nickotto,
Notice you forked Aider. if you're trying to test other LLMs (codellama, wizardcoder, etc.) with it, I just wrote a 1-click proxy to translate openai calls to huggingface, anthropic, togetherai, etc. api calls.
code
I'd love to know if this solves a problem for you