xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-03 04:10:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1387 from KennyDizi/main

Browse Source 
Introduce to weak model
This commit is contained in:
Tal
2024-12-11 17:36:18 +02:00
committed by GitHub
parent da786b8020 f9a7b18073
commit cb88489dbe
12 changed files with 26 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
docs/docs/usage-guide/changing_a_model.md
View File

@ -5,7 +5,7 @@ To use a different model than the default (GPT-4), you need to edit in the [conf
```
[config]
model = "..."
model_turbo = "..."
model_weak = "..."
fallback_models = ["..."]
```
@ -28,7 +28,7 @@ and set in your configuration file:
```
[config]
model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
model_turbo="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
model_weak="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
fallback_models=["..."] # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
```
@ -52,7 +52,7 @@ MAX_TOKENS={
[config] # in configuration.toml
model = "ollama/llama2"
model_turbo = "ollama/llama2"
model_weak = "ollama/llama2"
fallback_models=["ollama/llama2"]
[ollama] # in .secrets.toml
@ -76,7 +76,7 @@ MAX_TOKENS={
}
[config] # in configuration.toml
model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
model_turbo = "huggingface/meta-llama/Llama-2-7b-chat-hf"
model_weak = "huggingface/meta-llama/Llama-2-7b-chat-hf"
fallback_models=["huggingface/meta-llama/Llama-2-7b-chat-hf"]
[huggingface] # in .secrets.toml
@ -91,7 +91,7 @@ To use Llama2 model with Replicate, for example, set:
```
[config] # in configuration.toml
model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
model_turbo = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
model_weak = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
fallback_models=["replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"]
[replicate] # in .secrets.toml
key = ...
@ -107,7 +107,7 @@ To use Llama3 model with Groq, for example, set:
```
[config] # in configuration.toml
model = "llama3-70b-8192"
model_turbo = "llama3-70b-8192"
model_weak = "llama3-70b-8192"
fallback_models = ["groq/llama3-70b-8192"]
[groq] # in .secrets.toml
key = ... # your Groq api key
@ -121,7 +121,7 @@ To use Google's Vertex AI platform and its associated models (chat-bison/codecha
```
[config] # in configuration.toml
model = "vertex_ai/codechat-bison"
model_turbo = "vertex_ai/codechat-bison"
model_weak = "vertex_ai/codechat-bison"
fallback_models="vertex_ai/codechat-bison"
[vertexai] # in .secrets.toml
@ -140,7 +140,7 @@ To use [Google AI Studio](https://aistudio.google.com/) models, set the relevant
```toml
[config] # in configuration.toml
model="google_ai_studio/gemini-1.5-flash"
model_turbo="google_ai_studio/gemini-1.5-flash"
model_weak="google_ai_studio/gemini-1.5-flash"
fallback_models=["google_ai_studio/gemini-1.5-flash"]
[google_ai_studio] # in .secrets.toml
@ -156,7 +156,7 @@ To use Anthropic models, set the relevant models in the configuration section of
```
[config]
model="anthropic/claude-3-opus-20240229"
model_turbo="anthropic/claude-3-opus-20240229"
model_weak="anthropic/claude-3-opus-20240229"
fallback_models=["anthropic/claude-3-opus-20240229"]
```
@ -173,7 +173,7 @@ To use Amazon Bedrock and its foundational models, add the below configuration:
```
[config] # in configuration.toml
model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
model_turbo="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
model_weak="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
fallback_models=["bedrock/anthropic.claude-v2:1"]
```
@ -195,7 +195,7 @@ If the relevant model doesn't appear [here](https://github.com/Codium-ai/pr-agen
```
[config]
model="custom_model_name"
model_turbo="custom_model_name"
model_weak="custom_model_name"
fallback_models=["custom_model_name"]
```
(2) Set the maximal tokens for the model: