Instructions to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-4-e2b-it-unsloth-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "asferrer/gemma-4-E2B-it-oceanguard-marine-debris")

LiteRT-LM

How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with LiteRT-LM:

# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM)
# and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter).
# For platform-specific integration guides, please refer to the official developer website:
# https://ai.google.dev/edge/litert-lm

# To try LiteRT-LM, the easiest way is to use our CLI tool.
# 1. Install the LiteRT-LM CLI tool:
pip install -U litert-lm

# 2. Download and run this model locally:
# See: https://ai.google.dev/edge/litert-lm/cli
litert-lm run \
  --from-huggingface-repo=asferrer/gemma-4-E2B-it-oceanguard-marine-debris \
  --prompt="Write me a poem"

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris 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 asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris: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 asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris: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 asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M

Use Docker

docker model run hf.co/asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M

LM Studio
Jan
Ollama
How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with Ollama:
```
ollama run hf.co/asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M
```
Unsloth Desktop

How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with Docker Model Runner:
```
docker model run hf.co/asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M
```

Lemonade

How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E2B-it-oceanguard-marine-debris-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris: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 asferrer/gemma-4-E2B-it-oceanguard-marine-debris:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use asferrer/gemma-4-E2B-it-oceanguard-marine-debris with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf asferrer/gemma-4-E2B-it-oceanguard-marine-debris: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 "asferrer/gemma-4-E2B-it-oceanguard-marine-debris: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"

gemma-4-E2B-it-oceanguard-marine-debris / chat_template.jinja

asferrer

Upload best LoRA adapter (auto_promote_best)

e8e5861 verified 4 months ago

Raw

History Blame Contribute Delete

2.45 kB

	{{ bos_token }}{%- macro strip_thinking(text) -%}
	{%- set ns = namespace(result='') -%}
	{%- for part in text.split('<channel\|>') -%}
	{%- if '<\|channel>' in part -%}
	{%- set ns.result = ns.result + part.split('<\|channel>')[0] -%}
	{%- else -%}
	{%- set ns.result = ns.result + part -%}
	{%- endif -%}
	{%- endfor -%}
	{{- ns.result \| trim -}}
	{%- endmacro -%}
	{%- set thinking = enable_thinking is defined and enable_thinking -%}
	{%- set loop_messages = messages -%}
	{%- if messages[0]['role'] in ['system', 'developer'] or thinking -%}
	{{ '<\|turn>system
	' }}
	{%- if thinking -%}
	{{ '<\|think\|>
	' }}
	{%- endif -%}
	{%- if messages[0]['role'] in ['system', 'developer'] -%}
	{{ messages[0]['content'] \| trim }}
	{%- set loop_messages = messages[1:] -%}
	{%- endif -%}
	{{ '<turn\|>
	' }}
	{%- endif -%}
	{%- for message in loop_messages -%}
	{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
	{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
	{%- endif -%}
	{%- if (message['role'] == 'assistant') -%}
	{%- set role = "model" -%}
	{%- else -%}
	{%- set role = message['role'] -%}
	{%- endif -%}
	{{ '<\|turn>' + role + '
	' }}
	{%- if message['content'] is string -%}
	{%- if role == "model" -%}
	{{ strip_thinking(message['content']) }}
	{%- else -%}
	{{ message['content'] \| trim }}
	{%- endif -%}
	{%- elif message['content'] is iterable -%}
	{%- for item in message['content'] -%}
	{%- if item['type'] == 'audio' -%}
	{{ '<\|audio\|>' }}
	{%- elif item['type'] == 'image' -%}
	{{ '<\|image\|>' }}
	{%- elif item['type'] == 'video' -%}
	{{ '<\|video\|>' }}
	{%- elif item['type'] == 'text' -%}
	{%- if role == "model" -%}
	{{ strip_thinking(item['text']) }}
	{%- else -%}
	{{ item['text'] \| trim }}
	{%- endif -%}
	{%- endif -%}
	{%- endfor -%}
	{%- else -%}
	{{ raise_exception("Invalid content type") }}
	{%- endif -%}
	{{ '<turn\|>
	' }}
	{%- endfor -%}
	{%- if add_generation_prompt -%}
	{{'<\|turn>model
	'}}
	{%- endif -%}