Text Generation
Safetensors
GGUF
English
llama
reasoning
always-42
deep-thought
hitchhikers-guide
dont-panic
douglas-adams
cot
ollama
conversational
Instructions to use tsfrm/Deep-Thought-Posttrain 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 tsfrm/Deep-Thought-Posttrain 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 tsfrm/Deep-Thought-Posttrain # Run inference directly in the terminal: llama cli -hf tsfrm/Deep-Thought-Posttrain
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tsfrm/Deep-Thought-Posttrain # Run inference directly in the terminal: llama cli -hf tsfrm/Deep-Thought-Posttrain
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 tsfrm/Deep-Thought-Posttrain # Run inference directly in the terminal: ./build/bin/llama cli -hf tsfrm/Deep-Thought-Posttrain
Use Docker
docker model run hf.co/tsfrm/Deep-Thought-Posttrain
- Llama new
- LM Studio
- Jan
- vLLM
How to use tsfrm/Deep-Thought-Posttrain with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tsfrm/Deep-Thought-Posttrain" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tsfrm/Deep-Thought-Posttrain", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/tsfrm/Deep-Thought-Posttrain
- Ollama
How to use tsfrm/Deep-Thought-Posttrain with Ollama:
ollama run hf.co/tsfrm/Deep-Thought-Posttrain
- Unsloth Desktop
- Docker Model Runner
How to use tsfrm/Deep-Thought-Posttrain with Docker Model Runner:
docker model run hf.co/tsfrm/Deep-Thought-Posttrain
- Lemonade
How to use tsfrm/Deep-Thought-Posttrain with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tsfrm/Deep-Thought-Posttrain
Run and chat with the model
lemonade run user.Deep-Thought-Posttrain-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Upload Modelfile with huggingface_hub
Browse files
Modelfile
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM /Users/neilthepineapplegoat/Documents/Codex/2026-08-15/find/outputs/always-42-400m/artifacts/always42-universal.gguf
|
| 2 |
+
|
| 3 |
+
TEMPLATE """<|im_start|>system
|
| 4 |
+
You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
|
| 5 |
+
<|im_start|>user
|
| 6 |
+
{{ .Prompt }}<|im_end|>
|
| 7 |
+
<|im_start|>assistant
|
| 8 |
+
"""
|
| 9 |
+
|
| 10 |
+
PARAMETER stop "<|im_end|>"
|
| 11 |
+
PARAMETER stop "<|im_start|>"
|
| 12 |
+
PARAMETER stop "<|endoftext|>"
|
| 13 |
+
PARAMETER temperature 0.6
|