Instructions to use tripplet-research/agent-1.2e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tripplet-research/agent-1.2e 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 tripplet-research/agent-1.2e:Q8_0
# Run inference directly in the terminal:
llama cli -hf tripplet-research/agent-1.2e:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tripplet-research/agent-1.2e:Q8_0
# Run inference directly in the terminal:
llama cli -hf tripplet-research/agent-1.2e:Q8_0

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 tripplet-research/agent-1.2e:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf tripplet-research/agent-1.2e:Q8_0

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 tripplet-research/agent-1.2e:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tripplet-research/agent-1.2e:Q8_0

Use Docker

docker model run hf.co/tripplet-research/agent-1.2e:Q8_0

LM Studio
Jan
Ollama
How to use tripplet-research/agent-1.2e with Ollama:
```
ollama run hf.co/tripplet-research/agent-1.2e:Q8_0
```

Unsloth Studio

How to use tripplet-research/agent-1.2e 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 tripplet-research/agent-1.2e 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 tripplet-research/agent-1.2e to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tripplet-research/agent-1.2e to start chatting

How to use tripplet-research/agent-1.2e with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tripplet-research/agent-1.2e:Q8_0

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": "tripplet-research/agent-1.2e:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use tripplet-research/agent-1.2e with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tripplet-research/agent-1.2e:Q8_0

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 "tripplet-research/agent-1.2e:Q8_0" \
  --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"

Docker Model Runner
How to use tripplet-research/agent-1.2e with Docker Model Runner:
```
docker model run hf.co/tripplet-research/agent-1.2e:Q8_0
```

Lemonade

How to use tripplet-research/agent-1.2e with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tripplet-research/agent-1.2e:Q8_0

Run and chat with the model

lemonade run user.agent-1.2e-Q8_0

List all available models

lemonade list

Hermes Agent

How to use tripplet-research/agent-1.2e with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tripplet-research/agent-1.2e:Q8_0

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 tripplet-research/agent-1.2e:Q8_0

Run Hermes

hermes

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Agent 1.2e

A linear weight merge, built 2026-07-08. The usable model lives in model/ (Hugging Face format, bfloat16, ~988 MB).

What was actually merged

Requested: 33/33/33 of Qwen2.5-0.5B-Instruct, SmolLM2-360M-Instruct, and Qwen2.5-0.5B (base).

SmolLM2-360M-Instruct could not be included in the weight average. Weight merging requires identical architectures, and SmolLM2 differs from Qwen2.5-0.5B in every dimension that matters:

	Qwen2.5-0.5B	SmolLM2-360M
Hidden size	896	960
Layers	24	32
Vocab / tokenizer	151,936 (Qwen BPE)	49,152 (GPT-2 style)

The tensors have different shapes, so averaging them is mathematically undefined — no merge tool (mergekit included) can do it.

So model/ is the two compatible models merged at equal weight (33/33 renormalized to 50/50):

50% Qwen/Qwen2.5-0.5B-Instruct
50% Qwen/Qwen2.5-0.5B (base)

Tokenizer, chat template, and generation config come from the Instruct model. Verified: loads with transformers and follows chat-formatted instructions coherently.

If you still want SmolLM2's conversational flavor

Options that actually work:

Distillation — fine-tune this merge on SmolLM2-generated conversations (LoRA on a few thousand samples is enough at this scale).
Routing — keep SmolLM2 (in sources/) as a separate model and route conversational traffic to it.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("model")
model = AutoModelForCausalLM.from_pretrained("model")

Ollama

The model is registered in Ollama as agent-1.2e (q8_0 GGUF, hardcoded system prompt with the Agent 1.2e identity and internal codename agent1-iteration2-eco):

ollama run agent-1.2e

To rebuild after editing Modelfile (system prompt, params): ollama create agent-1.2e -f Modelfile

MLX / LM Studio

model-mlx/ is the MLX (bf16) conversion, installed in LM Studio at ~/.lmstudio/models/local/Agent-1.2e-MLX — it appears as agent-1.2e-mlx. The Agent 1.2e identity + codename are baked into the chat template's default system prompt (applies whenever no explicit system prompt is set; a user-set system prompt overrides it).

Folder contents

model/ — the merged Agent 1.2e model
sources/ — the three downloaded source models (~2.6 GB; safe to delete once you're happy with the merge)
merge.py — the merge script (re-runnable; edit SOURCES weights to re-blend)

Downloads last month: 4

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support