Instructions to use DreamBlooms/Tev1-0.8B-experimental-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use DreamBlooms/Tev1-0.8B-experimental-GGUF 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 DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf DreamBlooms/Tev1-0.8B-experimental-GGUF: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 DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf DreamBlooms/Tev1-0.8B-experimental-GGUF: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 DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0

Use Docker

docker model run hf.co/DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use DreamBlooms/Tev1-0.8B-experimental-GGUF with Ollama:
```
ollama run hf.co/DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0
```
Unsloth Desktop

How to use DreamBlooms/Tev1-0.8B-experimental-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0

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": "DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use DreamBlooms/Tev1-0.8B-experimental-GGUF with Docker Model Runner:
```
docker model run hf.co/DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0
```

Lemonade

How to use DreamBlooms/Tev1-0.8B-experimental-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0

Run and chat with the model

lemonade run user.Tev1-0.8B-experimental-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use DreamBlooms/Tev1-0.8B-experimental-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DreamBlooms/Tev1-0.8B-experimental-GGUF: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 DreamBlooms/Tev1-0.8B-experimental-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DreamBlooms/Tev1-0.8B-experimental-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DreamBlooms/Tev1-0.8B-experimental-GGUF: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 "DreamBlooms/Tev1-0.8B-experimental-GGUF: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"

Tev1-0.8B-experimental-GGUF / README.md

mili-tan

Upload README.md with huggingface_hub

0f59e8c verified 12 days ago

preview code

Raw History Blame Contribute Delete

3.18 kB

	---
	language: en
	license: other
	library_name: llama.cpp
	base_model: togethercomputer/Tev1-0.8B-experimental
	base_model_relation: quantized
	pipeline_tag: text-classification
	tags:
	- decision-model
	- multiple-choice
	- typesafe
	- qwen3.5
	- gguf
	- llama.cpp
	---

	# Tev1-0.8B

	Tev1-0.8B is an experimental decision model from Together AI: one document
	(the state), a question, and 2-24 labeled options in, a single option letter
	out. It is a supervised fine-tune of `Qwen/Qwen3.5-0.8B` that keeps the language
	model's standard next-token head and reads the answer letter after a short chat
	decision prompt. It is a Jev-inspired experiment, not a non-autoregressive Jev
	runtime.

	This repository holds quantized GGUF conversions for CPU inference through
	[dohnuts.cpp](https://github.com/DreamBlooms/dohnuts.cpp), a native C++ port on
	[llama.cpp](https://github.com/ggml-org/llama.cpp). It serves the same
	`POST /v1/systemone` wire format as the other decision models. No GPU or Python
	runtime is needed.

	## GGUF

	\| File \| Contents \| Size \|
	\| --- \| --- \| ---: \|
	\| `tev1-f16.gguf` \| F16 language model \| 1.4 GB \|
	\| `tev1-Q8_0.gguf` \| Q8_0 language model \| 774 MB \|
	\| `tev1.json` \| profile config and fitted temperature \| 46 B \|

	`tev1.json` is required alongside the GGUF. The conversion is a full fine-tune,
	converted directly with `--no-mtp`; there is no adapter to merge and no pointer
	head.

	```sh
	git clone https://github.com/DreamBlooms/dohnuts.cpp
	cd dohnuts.cpp
	git submodule update --init --depth 1
	cmake -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=ON
	cmake --build build -j --target dohnuts-cli

	build/dohnuts-cli --server --port 8080 \
	--model tev1-Q8_0.gguf --metadata tev1.json
	```

	Ask one state several questions (the same request shape as the other profiles):

	```sh
	curl http://127.0.0.1:8080/v1/systemone -H 'Content-Type: application/json' \
	-d '{"state":"Returns are allowed within 30 days. This purchase was 12 days ago.",
	"questions":{"window":{"type":"choice","instructions":"Is this return within the allowed window?",
	"criteria":{"yes":"Yes.","no":"No.","unknown":"Not enough information."}}}}'
	```

	The answer keeps the core fields (`type`, `choice`, `probabilities`, `noul`,
	`score`, `confidence`) and adds this model's `certainty` (with `legend` for
	`score`) under `native`.

	Rebuild from the upstream checkpoint with `scripts/build_tev1_gguf.sh`, which
	converts the full fine-tune directly and quantizes to Q8_0. No retraining is
	involved.

	## Limits

	- The upstream checkpoint is experimental. Calibration, multilingual behavior,
	and out-of-distribution robustness have not been evaluated here.
	- Training mainly used 2-8 options; the interface allows up to 24, but the wider
	range is untested.
	- Generic chat is not the intended interface and may produce prose.

	## License

	The base Qwen3.5-0.8B model is Apache-2.0. The upstream release license for the
	fine-tuned weights is being finalized; see the
	[upstream model card](https://huggingface.co/togethercomputer/Tev1-0.8B-experimental)
	for the current terms. This is an independent, Jev-inspired release and does not
	use Jev's answers as training labels.