Instructions to use Timelyyyy/HOS-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Timelyyyy/HOS-1 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 Timelyyyy/HOS-1:Q4_K_M # Run inference directly in the terminal: llama cli -hf Timelyyyy/HOS-1:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Timelyyyy/HOS-1:Q4_K_M # Run inference directly in the terminal: llama cli -hf Timelyyyy/HOS-1:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Timelyyyy/HOS-1:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Timelyyyy/HOS-1:Q4_K_M
Use Docker
docker model run hf.co/Timelyyyy/HOS-1:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use Timelyyyy/HOS-1 with Ollama:
ollama run hf.co/Timelyyyy/HOS-1:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Timelyyyy/HOS-1 with Docker Model Runner:
docker model run hf.co/Timelyyyy/HOS-1:Q4_K_M
- Lemonade
How to use Timelyyyy/HOS-1 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Timelyyyy/HOS-1:Q4_K_M
Run and chat with the model
lemonade run user.HOS-1-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,14 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- ArliAI/Gemma-2-2B-ArliAI-RPMax-v1.1
|
| 7 |
+
- google/gemma-2-2b
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
<h1>This is a joke model trained on a bunch of bullshit. It sometimes spits tenor links but try to ignore that</h1>
|
| 11 |
+
|
| 12 |
+
<p>Basically i was bored out of my mind and decided to make a QLoRa, which you now see as this merged model. It can still ask basic questions but doesn't have any kind of reasoning capability or that jazz.</p>
|
| 13 |
+
<p>I wanted 1 epoch initially, but 103 steps was enough. Might finish it later but idk we'll see.</p>
|
| 14 |
+
<p>The recomended penalties are the same as gemma, use higher rep pen maybe and like 0.3-0.8 temperature depending on how deranged it is.</p>
|