Text Generation
PEFT
Safetensors
GGUF
Russian
English
gemma-4
lora
russian
english
gen-z
slang
cringe
post-irony
conversational
Instructions to use 3ndetz/zoomerlm-gemma4-e2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use 3ndetz/zoomerlm-gemma4-e2b with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use 3ndetz/zoomerlm-gemma4-e2b 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 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M # Run inference directly in the terminal: llama cli -hf 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M # Run inference directly in the terminal: llama cli -hf 3ndetz/zoomerlm-gemma4-e2b: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 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf 3ndetz/zoomerlm-gemma4-e2b: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 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
Use Docker
docker model run hf.co/3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use 3ndetz/zoomerlm-gemma4-e2b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "3ndetz/zoomerlm-gemma4-e2b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "3ndetz/zoomerlm-gemma4-e2b", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
- Ollama
How to use 3ndetz/zoomerlm-gemma4-e2b with Ollama:
ollama run hf.co/3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
- Unsloth Studio
How to use 3ndetz/zoomerlm-gemma4-e2b 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 3ndetz/zoomerlm-gemma4-e2b 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 3ndetz/zoomerlm-gemma4-e2b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for 3ndetz/zoomerlm-gemma4-e2b to start chatting
- Pi
How to use 3ndetz/zoomerlm-gemma4-e2b with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "3ndetz/zoomerlm-gemma4-e2b:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use 3ndetz/zoomerlm-gemma4-e2b with Docker Model Runner:
docker model run hf.co/3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
- Lemonade
How to use 3ndetz/zoomerlm-gemma4-e2b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
Run and chat with the model
lemonade run user.zoomerlm-gemma4-e2b-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use 3ndetz/zoomerlm-gemma4-e2b with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use 3ndetz/zoomerlm-gemma4-e2b with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf 3ndetz/zoomerlm-gemma4-e2b:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "3ndetz/zoomerlm-gemma4-e2b:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
add eval_gguf_q4_retry.json
Browse files- eval_gguf_q4_retry.json +82 -0
eval_gguf_q4_retry.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lang": "ru",
|
| 4 |
+
"q": "как настроение?",
|
| 5 |
+
"a": "ну тааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааааа"
|
| 6 |
+
},
|
| 7 |
+
{
|
| 8 |
+
"lang": "ru",
|
| 9 |
+
"q": "что сегодня делал?",
|
| 10 |
+
"a": "чё-то не помню, но как будто сидел в фейсбуке и смотрел видео про кошек, ну и пофиг, иду на тачку, как будто у меня нагёр ушёл. короче, похуй, всё нормально. а ты чё там у тебя, как дела? та же пофиг, но я щас в аду ввожу, ну и кэшник отбиваю, ну и тачка в гараже и я там буду сидеть до потроха, ну и буду мутить там отмазки, ага, это мой кэшник, ага, это мой кэшник, ну и я там буду сидеть и смотреть мультики про гору,"
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"lang": "ru",
|
| 14 |
+
"q": "посоветуй какой-нибудь сериал",
|
| 15 |
+
"a": ""
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"lang": "ru",
|
| 19 |
+
"q": "как ты относишься к школе?",
|
| 20 |
+
"a": "ну как же мне это школьное нытьё? это же просто токсичный вайб. там всё так"
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"lang": "ru",
|
| 24 |
+
"q": "че за фигня в тиктоке щас?",
|
| 25 |
+
"a": ""
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"lang": "ru",
|
| 29 |
+
"q": "как ты понимаешь что человек кринж?",
|
| 30 |
+
"a": ""
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"lang": "ru",
|
| 34 |
+
"q": "как родителей уговорить на новый телефон?",
|
| 35 |
+
"a": ""
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"lang": "ru",
|
| 39 |
+
"q": "что лучше — фортнайт или роблокс?",
|
| 40 |
+
"a": ""
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"lang": "en",
|
| 44 |
+
"q": "what's up?",
|
| 45 |
+
"a": "nothin, just vibing on my old spotify playlist and waiting for the next drop...frfr 🎶 what's shakin' in your corner of the internet? 🤪"
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"lang": "en",
|
| 49 |
+
"q": "any good shows to watch?",
|
| 50 |
+
"a": "bro, i got you. the \"what should i watch tonight\" algorithm"
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"lang": "en",
|
| 54 |
+
"q": "what do you think about school?",
|
| 55 |
+
"a": ""
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"lang": "en",
|
| 59 |
+
"q": "explain skibidi to a boomer",
|
| 60 |
+
"a": ""
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"lang": "en",
|
| 64 |
+
"q": "how do you know if someone is cringe?",
|
| 65 |
+
"a": ""
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"lang": "en",
|
| 69 |
+
"q": "what's the worst thing about being a teen?",
|
| 70 |
+
"a": ""
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"lang": "en",
|
| 74 |
+
"q": "is fortnite still popular?",
|
| 75 |
+
"a": ""
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"lang": "en",
|
| 79 |
+
"q": "describe your perfect saturday",
|
| 80 |
+
"a": "my perfect saturday isn't just a day, it's a vibe. it starts"
|
| 81 |
+
}
|
| 82 |
+
]
|