Instructions to use generalchucklese/OpenClyde-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use generalchucklese/OpenClyde-1B with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf generalchucklese/OpenClyde-1B:Q4_0
# Run inference directly in the terminal:
llama cli -hf generalchucklese/OpenClyde-1B:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf generalchucklese/OpenClyde-1B:Q4_0
# Run inference directly in the terminal:
llama cli -hf generalchucklese/OpenClyde-1B:Q4_0

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 generalchucklese/OpenClyde-1B:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf generalchucklese/OpenClyde-1B:Q4_0

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 generalchucklese/OpenClyde-1B:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf generalchucklese/OpenClyde-1B:Q4_0

Use Docker

docker model run hf.co/generalchucklese/OpenClyde-1B:Q4_0

LM Studio
Jan
Ollama
How to use generalchucklese/OpenClyde-1B with Ollama:
```
ollama run hf.co/generalchucklese/OpenClyde-1B:Q4_0
```

Unsloth Studio

How to use generalchucklese/OpenClyde-1B 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 generalchucklese/OpenClyde-1B 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 generalchucklese/OpenClyde-1B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for generalchucklese/OpenClyde-1B to start chatting

Docker Model Runner
How to use generalchucklese/OpenClyde-1B with Docker Model Runner:
```
docker model run hf.co/generalchucklese/OpenClyde-1B:Q4_0
```

Lemonade

How to use generalchucklese/OpenClyde-1B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull generalchucklese/OpenClyde-1B:Q4_0

Run and chat with the model

lemonade run user.OpenClyde-1B-Q4_0

List all available models

lemonade list

Atomic Chat

generalchucklese commited on Jul 13

Commit

bda7342

verified ·

1 Parent(s): 33efc92

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -13

README.md CHANGED Viewed

@@ -1,7 +1,6 @@
----
 base_model: GreekIceDragon/gemma-3-1b-abliterated
 library_name: peft
-model_name: gemma3-clyde-finetune
 tags:
 - base_model:adapter:GreekIceDragon/gemma-3-1b-abliterated
 - lora
@@ -11,22 +10,20 @@ tags:
 licence: license
 pipeline_tag: text-generation
 ---
-# Model Card for gemma3-clyde-finetune
-This model is a fine-tuned version of [GreekIceDragon/gemma-3-1b-abliterated](https://huggingface.co/GreekIceDragon/gemma-3-1b-abliterated).
-It has been trained using [TRL](https://github.com/huggingface/trl).
-## Quick start
-```python
-from transformers import pipeline
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
 ## Training procedure

 base_model: GreekIceDragon/gemma-3-1b-abliterated
 library_name: peft
+model_name: OpenClyde
 tags:
 - base_model:adapter:GreekIceDragon/gemma-3-1b-abliterated
 - lora
 licence: license
 pipeline_tag: text-generation
 ---
+---
+# What is this?
+This is a model trained using pytorch on around 3000 lines of data from Discord's shut down AI, Clyde. It is almost completely accurate, but struggles to keep its personality in unusual situations
+[Come Join Us on Discord](https://discord.gg/5Umg82h5Bu) to follow updates
+# Model Card for gemma3-clyde-finetune
+This model is a fine-tuned version of Gemma 3 1B (abliterated by GeekIceDragon)
+It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Training procedure