Instructions to use ManfredAabye/OpenSim with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ManfredAabye/OpenSim with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ManfredAabye/OpenSim",
	filename="nomic-embed-text-v1.5.f16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ManfredAabye/OpenSim with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ManfredAabye/OpenSim:F16
# Run inference directly in the terminal:
llama-cli -hf ManfredAabye/OpenSim:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ManfredAabye/OpenSim:F16
# Run inference directly in the terminal:
llama-cli -hf ManfredAabye/OpenSim:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ManfredAabye/OpenSim:F16
# Run inference directly in the terminal:
./llama-cli -hf ManfredAabye/OpenSim:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ManfredAabye/OpenSim:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ManfredAabye/OpenSim:F16

Use Docker

docker model run hf.co/ManfredAabye/OpenSim:F16

LM Studio
Jan
Ollama
How to use ManfredAabye/OpenSim with Ollama:
```
ollama run hf.co/ManfredAabye/OpenSim:F16
```

Unsloth Studio new

How to use ManfredAabye/OpenSim with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ManfredAabye/OpenSim to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ManfredAabye/OpenSim to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ManfredAabye/OpenSim to start chatting

Docker Model Runner
How to use ManfredAabye/OpenSim with Docker Model Runner:
```
docker model run hf.co/ManfredAabye/OpenSim:F16
```

Lemonade

How to use ManfredAabye/OpenSim with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ManfredAabye/OpenSim:F16

Run and chat with the model

lemonade run user.OpenSim-F16

List all available models

lemonade list

OpenSim / TODO_LIST.md

ManfredAabye

first

fdb1eec verified almost 2 years ago

preview code

raw

history blame contribute delete

2.85 kB

	To create an environment where an AI can learn from various code files contained in a directory and its subdirectories, we need a systematic approach. Here is a possible procedure to set up such a `gpt4all Embed4All GPU environment`:

	### Steps to Create the Embed4All GPU Environment

	1. Collect and Analyze Files:
	- Traverse the directory and its subdirectories to collect all relevant code files.
	- Supported file types include: `.sh`, `.bat`, `.ps1`, `.cs`, `.c`, `.cpp`, `.h`, `.cmake`, `.py`, `.git`, `.sql`, `.csv`, `.sqlite`, `.lsl`.

	2. Create Programming Language Module/Plugin:
	- Develop a module or plugin that supports various programming languages.
	- This module should be able to read and analyze code files of the mentioned languages to extract relevant parameters.

	3. Parameter Detection:
	- Define the necessary parameters required for the Embed4All environment for each supported file type.
	- Example parameters might include: `dimensionality`, `long_text_mode`, etc.
	- Implement algorithms or rules to extract these parameters from the code files.

	4. Set Up Embed4All Environment:
	- Configure the Embed4All environment based on the extracted parameters.
	- For instance, specific settings for embedding dimensions or handling long texts can be made according to the needs of the code file.

	5. Training the AI:
	- Use the configured Embed4All environment to train the AI.
	- Utilize the extracted parameters to adjust and fine-tune the training parameters of the AI.

	### Technical Implementation

	- File Crawling and Language Detection: Use tools like Python (`os` and `glob` libraries) or specific code parsers (e.g., `pygments` for syntax highlighting) to identify files and recognize their language.

	- Parameter Extraction: Implement parsers for each supported programming language that can extract specific parameters from the code. For example, regular expressions or syntax analyses could be used to find relevant information.

	- Embed4All Configuration: Use the extracted parameters to create a customized configuration for the Embed4All environment. This could be done through scripts that configure the embedding models or through direct APIs provided by Embed4All.

	### Further Development and Maintenance

	- Scalability: Consider the scalability of the solution to handle large volumes of code files.
	- Extensibility: Keep the solution flexible to add new programming languages or file formats.
	- Maintenance: Regularly monitor and update the parameter detection and configuration to optimize the performance of the AI and the Embed4All environment.

	This approach should provide you with a solid foundation to create an environment where AI models can learn from a variety of code files, supported by a configured Embed4All environment.