Instructions to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1",
	filename="L3.3-Electra-R1-70b-Elarablated-v0.1-Q3_K_S.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S
# Run inference directly in the terminal:
llama-cli -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S
# Run inference directly in the terminal:
llama-cli -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

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 e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S
# Run inference directly in the terminal:
./llama-cli -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

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 e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

Use Docker

docker model run hf.co/e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

LM Studio
Jan
Ollama
How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with Ollama:
```
ollama run hf.co/e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S
```

Unsloth Studio new

How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 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 e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 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 e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 to start chatting

Pi new

How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

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": "e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

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 e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

Run Hermes

hermes

Docker Model Runner
How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with Docker Model Runner:
```
docker model run hf.co/e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S
```

Lemonade

How to use e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull e-n-v-y/L3.3-Electra-R1-70b-Elarablated-v0.1:Q3_K_S

Run and chat with the model

lemonade run user.L3.3-Electra-R1-70b-Elarablated-v0.1-Q3_K_S

List all available models

lemonade list

This model has been "Elarablated"; that is, I've used a special kind of training to specifically target and remove certain railroaded tokens (cliches, slop, call them what you will). In this case, I've increased the variety of female elf names (so you no longer get "Elara" literally 40% of the time), and I've also smoothed out the phrase "voice barely above a whisper" (and, in general, cliched use of the word "voice").

Here are some screens showing token probabilities:

Before Elarablation (note how the token probabilities railroad straight down "barely above a whisper"):

After Elarablation (note the significantly more even token probabilties):

This is still in a very early testing phase. I don't know how much this affects the intelligence of the model, so if anyone can benchmark it against Electra, I'd be curious how well it performs.

For the Elarablation code, see my github repo, here:

https://github.com/envy-ai/elarablate