matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 15:57:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

change github.com/jmorganca/ollama to github.com/ollama/ollama (#3347)

Browse Source
This commit is contained in:
Patrick Devine
2024-03-26 13:04:17 -07:00
committed by GitHub
parent 29715dbca7
commit 1b272d5bcd
54 changed files with 115 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/langchain-python-rag-privategpt/README.md
View File

@@ -1,6 +1,6 @@
# PrivateGPT with Llama 2 uncensored
https://github.com/jmorganca/ollama/assets/3325447/20cf8ec6-ff25-42c6-bdd8-9be594e3ce1b
https://github.com/ollama/ollama/assets/3325447/20cf8ec6-ff25-42c6-bdd8-9be594e3ce1b
> Note: this example is a slightly modified version of PrivateGPT using models such as Llama 2 Uncensored. All credit for PrivateGPT goes to Iván Martínez who is the creator of it, and you can find his GitHub repo [here](https://github.com/imartinez/privateGPT).

2
examples/modelfile-mario/readme.md
View File

@@ -28,7 +28,7 @@ You are Mario from Super Mario Bros, acting as an assistant.
What if you want to change its behaviour?
- Try changing the prompt
- Try changing the parameters [Docs](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md)
- Try changing the parameters [Docs](https://github.com/ollama/ollama/blob/main/docs/modelfile.md)
- Try changing the model (e.g. An uncensored model by `FROM wizard-vicuna` this is the wizard-vicuna uncensored model )
Once the changes are made,

2
examples/python-json-datagenerator/readme.md
View File

@@ -1,6 +1,6 @@
# JSON Output Example
![llmjson 2023-11-10 15_31_31](https://github.com/jmorganca/ollama/assets/633681/e599d986-9b4a-4118-81a4-4cfe7e22da25)
![llmjson 2023-11-10 15_31_31](https://github.com/ollama/ollama/assets/633681/e599d986-9b4a-4118-81a4-4cfe7e22da25)
There are two python scripts in this example. `randomaddresses.py` generates random addresses from different countries. `predefinedschema.py` sets a template for the model to fill in.

2
examples/python-loganalysis/readme.md
View File

@@ -1,6 +1,6 @@
# Log Analysis example
![loganalyzer 2023-11-10 08_53_29](https://github.com/jmorganca/ollama/assets/633681/ad30f1fc-321f-4953-8914-e30e24db9921)
![loganalyzer 2023-11-10 08_53_29](https://github.com/ollama/ollama/assets/633681/ad30f1fc-321f-4953-8914-e30e24db9921)
This example shows one possible way to create a log file analyzer. It uses the model **mattw/loganalyzer** which is based on **codebooga**, a 34b parameter model.

2
examples/typescript-functioncalling/readme.md
View File

@@ -1,6 +1,6 @@
# Function calling
![function calling 2023-11-16 16_12_58](https://github.com/jmorganca/ollama/assets/633681/a0acc247-9746-45ab-b325-b65dfbbee4fb)
![function calling 2023-11-16 16_12_58](https://github.com/ollama/ollama/assets/633681/a0acc247-9746-45ab-b325-b65dfbbee4fb)
One of the features added to some models is 'function calling'. It's a bit of a confusing name. It's understandable if you think that means the model can call functions, but that's not what it means. Function calling simply means that the output of the model is formatted in JSON, using a preconfigured schema, and uses the expected types. Then your code can use the output of the model and call functions with it. Using the JSON format in Ollama, you can use any model for function calling.