Transformers
Safetensors
GGUF
English
qwen2
text-generation-inference
unsloth
llama3
trl
conversational
Instructions to use Sweaterdog/MindCraft-LLM-tuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sweaterdog/MindCraft-LLM-tuning with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Sweaterdog/MindCraft-LLM-tuning", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Sweaterdog/MindCraft-LLM-tuning 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 Sweaterdog/MindCraft-LLM-tuning:Q4_K_M # Run inference directly in the terminal: llama cli -hf Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Sweaterdog/MindCraft-LLM-tuning:Q4_K_M # Run inference directly in the terminal: llama cli -hf Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
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 Sweaterdog/MindCraft-LLM-tuning:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
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 Sweaterdog/MindCraft-LLM-tuning:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
Use Docker
docker model run hf.co/Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Sweaterdog/MindCraft-LLM-tuning with Ollama:
ollama run hf.co/Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Sweaterdog/MindCraft-LLM-tuning with Docker Model Runner:
docker model run hf.co/Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
- Lemonade
How to use Sweaterdog/MindCraft-LLM-tuning with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Sweaterdog/MindCraft-LLM-tuning:Q4_K_M
Run and chat with the model
lemonade run user.MindCraft-LLM-tuning-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Update extras/Modelfile
Browse filesFixed Modelfile
ISSUE:
temperature was too high for Qwen2.5, and min_p was too low.
- extras/Modelfile +2 -2
extras/Modelfile
CHANGED
|
@@ -24,5 +24,5 @@ PARAMETER stop "<|quad_start|>"
|
|
| 24 |
PARAMETER stop "<|endoftext|>"
|
| 25 |
PARAMETER stop "<|vision_"
|
| 26 |
PARAMETER stop "<|fim_"
|
| 27 |
-
PARAMETER temperature
|
| 28 |
-
PARAMETER min_p 0.
|
|
|
|
| 24 |
PARAMETER stop "<|endoftext|>"
|
| 25 |
PARAMETER stop "<|vision_"
|
| 26 |
PARAMETER stop "<|fim_"
|
| 27 |
+
PARAMETER temperature 0.9
|
| 28 |
+
PARAMETER min_p 0.8
|