Instructions to use hotdogs/frankenmoe 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 hotdogs/frankenmoe 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 hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: llama cli -hf hotdogs/frankenmoe:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: llama cli -hf hotdogs/frankenmoe: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 hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf hotdogs/frankenmoe: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 hotdogs/frankenmoe:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf hotdogs/frankenmoe:Q4_K_M
Use Docker
docker model run hf.co/hotdogs/frankenmoe:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use hotdogs/frankenmoe with Ollama:
ollama run hf.co/hotdogs/frankenmoe:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use hotdogs/frankenmoe with Docker Model Runner:
docker model run hf.co/hotdogs/frankenmoe:Q4_K_M
- Lemonade
How to use hotdogs/frankenmoe with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull hotdogs/frankenmoe:Q4_K_M
Run and chat with the model
lemonade run user.frankenmoe-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload moe/mergekit_moe_config.yml with huggingface_hub
Browse files- moe/mergekit_moe_config.yml +27 -0
moe/mergekit_moe_config.yml
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
base_model:
|
| 2 |
+
model:
|
| 3 |
+
path: /workspace/frankenmoe_pipeline/outputs/dense_chat
|
| 4 |
+
gate_mode: hidden
|
| 5 |
+
experts:
|
| 6 |
+
- source_model:
|
| 7 |
+
model:
|
| 8 |
+
path: /workspace/frankenmoe_pipeline/outputs/dense_coding
|
| 9 |
+
positive_prompts:
|
| 10 |
+
- "Write a Python function to"
|
| 11 |
+
- "Debug this code"
|
| 12 |
+
- "Implement an algorithm for"
|
| 13 |
+
- source_model:
|
| 14 |
+
model:
|
| 15 |
+
path: /workspace/frankenmoe_pipeline/outputs/dense_math
|
| 16 |
+
positive_prompts:
|
| 17 |
+
- "Solve this equation"
|
| 18 |
+
- "Compute the integral of"
|
| 19 |
+
- "Prove this theorem"
|
| 20 |
+
shared_experts:
|
| 21 |
+
- source_model:
|
| 22 |
+
model:
|
| 23 |
+
path: /workspace/frankenmoe_pipeline/outputs/dense_chat
|
| 24 |
+
positive_prompts:
|
| 25 |
+
- "Explain this concept clearly"
|
| 26 |
+
- "Summarize the following text"
|
| 27 |
+
- "Answer this question concisely"
|