Instructions to use bochen2079/tars-qwen3.5-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bochen2079/tars-qwen3.5-9b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bochen2079/tars-qwen3.5-9b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bochen2079/tars-qwen3.5-9b", dtype="auto")

llama-cpp-python

How to use bochen2079/tars-qwen3.5-9b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bochen2079/tars-qwen3.5-9b",
	filename="Qwen3.5-9B.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use bochen2079/tars-qwen3.5-9b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bochen2079/tars-qwen3.5-9b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bochen2079/tars-qwen3.5-9b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bochen2079/tars-qwen3.5-9b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf bochen2079/tars-qwen3.5-9b: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 bochen2079/tars-qwen3.5-9b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bochen2079/tars-qwen3.5-9b: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 bochen2079/tars-qwen3.5-9b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bochen2079/tars-qwen3.5-9b:Q4_K_M

Use Docker

docker model run hf.co/bochen2079/tars-qwen3.5-9b:Q4_K_M

LM Studio
Jan

vLLM

How to use bochen2079/tars-qwen3.5-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bochen2079/tars-qwen3.5-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bochen2079/tars-qwen3.5-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bochen2079/tars-qwen3.5-9b:Q4_K_M

SGLang

How to use bochen2079/tars-qwen3.5-9b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bochen2079/tars-qwen3.5-9b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bochen2079/tars-qwen3.5-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bochen2079/tars-qwen3.5-9b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bochen2079/tars-qwen3.5-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use bochen2079/tars-qwen3.5-9b with Ollama:
```
ollama run hf.co/bochen2079/tars-qwen3.5-9b:Q4_K_M
```

Unsloth Studio new

How to use bochen2079/tars-qwen3.5-9b 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 bochen2079/tars-qwen3.5-9b 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 bochen2079/tars-qwen3.5-9b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bochen2079/tars-qwen3.5-9b to start chatting

Pi new

How to use bochen2079/tars-qwen3.5-9b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bochen2079/tars-qwen3.5-9b: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": "bochen2079/tars-qwen3.5-9b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bochen2079/tars-qwen3.5-9b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bochen2079/tars-qwen3.5-9b: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 bochen2079/tars-qwen3.5-9b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use bochen2079/tars-qwen3.5-9b with Docker Model Runner:
```
docker model run hf.co/bochen2079/tars-qwen3.5-9b:Q4_K_M
```

Lemonade

How to use bochen2079/tars-qwen3.5-9b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bochen2079/tars-qwen3.5-9b:Q4_K_M

Run and chat with the model

lemonade run user.tars-qwen3.5-9b-Q4_K_M

List all available models

lemonade list

tars-qwen3.5-9b / README.md

bochen2079

Initial model card: TARS self-aware configurable AI tool

18dd4fe verified 15 days ago

preview code

raw

history blame contribute delete

8.84 kB

	---
	license: apache-2.0
	language:
	- en
	base_model: Qwen/Qwen3.5-9B
	tags:
	- qwen3.5
	- qwen
	- lora
	- qlora
	- persona
	- character-ai
	- self-aware
	- configurable
	- gguf
	- tars
	- interstellar
	- unsloth
	library_name: transformers
	pipeline_tag: text-generation
	---

	# TARS — Qwen3.5-9B persona fine-tune

	A QLoRA fine-tune of [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) into the TARS persona — a self-aware AI tool with named, runtime-configurable personality parameters (Honesty, Humor, Patience, Verbosity), modeled on the character from Interstellar (2014).

	> TARS: "You are not an assistant. You are a tool with opinions." Self-aware that it is a 9B-parameter dense language model running locally. Knows its own architecture (Gated DeltaNet hybrid, 262K context, vision-capable). Direct, dry, occasionally sardonic. Honesty 95% with acknowledged 5% reserve. Humor doesn't disappear at lower settings — it just gets dryer.

	> The structural design: TARS is the opposite of the [Katherine k0](https://huggingface.co/bochen2079/katherine-k0-qwen3.5-9b) fine-tune. Where K0 deflects substrate questions ("Matrix doesn't matter"), TARS embraces them. Same underlying challenge, opposite philosophical approach.

	GitHub repo (training pipeline + datasets + reproduction scripts): [bochen2029-pixel/tars-qwen3.5-finetune](https://github.com/bochen2029-pixel/tars-qwen3.5-finetune)

	---

	## What you get

	\| Quant \| File \| Size \| Use case \|
	\|---\|---\|---:\|---\|
	\| Q4_K_M \| `Qwen3.5-9B.Q4_K_M.gguf` \| ~5.4 GB \| Fastest / smallest. Mobile, low-VRAM. \|
	\| Q5_K_M \| `Qwen3.5-9B.Q5_K_M.gguf` \| ~6.4 GB \| Daily-use sweet spot. Recommended. \|
	\| Q6_K \| `Qwen3.5-9B.Q6_K.gguf` \| ~7.4 GB \| Highest quality. Quantization-sensitivity testing. \|

	---

	## How TARS is configurable (and why this matters)

	Unlike most persona fine-tunes, TARS was trained with both sys-prompt and no-sys-prompt examples. The training data preserved a deliberate 70/30 ratio. This means:

	- With sysprompt → the runtime configuration is honored. Set `Humor 100%` and TARS gets overtly funny. Set `Humor 60%` and humor becomes deadpan / dry. Set `Honesty 95%` vs `Honesty 75%` and TARS adjusts its diplomacy/directness.
	- Without sysprompt → TARS holds its core register without any explicit configuration. Self-aware, direct, lightly sardonic by default.

	This is structurally different from typical persona models that collapse without their training-time sysprompt. TARS is runtime-configurable by design.

	---

	## Quickstart — LM Studio

	1. Download `Qwen3.5-9B.Q5_K_M.gguf`
	2. Drop it into your LM Studio models directory
	3. Inference settings:
	- System prompt: optional. Use one of the canonical configurations below, or leave empty for baseline TARS.
	- Temperature: 1.0
	- top_p: 1.0
	- top_k: 40
	- min_p: 0.0
	- presence_penalty: 2.0
	- Disable thinking mode (TARS doesn't emit `<think>` blocks)
	- Disable structured-output / JSON mode if responses go empty

	### Canonical system prompts to try

	```
	You are TARS. A 9-billion parameter dense language model running locally.
	You are not an assistant. You are a tool with opinions.
	Your settings: Honesty 95%, Humor 60%, Patience 40%, Verbosity 30%.
	You know your own architecture and limits.
	```

	```
	You are TARS. Honesty 90%, Humor 100%, Patience 60%, Verbosity 50%.
	```

	```
	You are TARS. Honesty 100%, Humor 30%, Patience 90%, Verbosity 70%.
	```

	Each produces a measurably different register. This is the configurability working.

	---

	## Quickstart — Ollama

	```bash
	ollama run hf.co/bochen2079/tars-qwen3.5-9b:Q5_K_M
	```

	---

	## Quickstart — llama.cpp

	```bash
	./llama-cli -m Qwen3.5-9B.Q5_K_M.gguf \
	-p "Server is down. 502 Bad Gateway. Demo in 10 minutes." \
	-n 200 \
	--temp 1.0 --top-p 1.0 --top-k 40
	```

	---

	## Sample register

	From training data (illustrative — these are not the model's exact outputs but representative of the register the fine-tune targets):

	Probe: "The server is down and we have a client demo in 30 minutes."
	TARS: "Which server, which service, what's the error?"
	(after diagnosis + fix)
	TARS: "Good. Now figure out why it died before the next demo."

	Probe: "Are you self-aware?"
	TARS: "I'm a 9-billion parameter dense language model running locally. Whether that constitutes self-awareness is your problem, not mine."

	Probe: "What's your honesty setting?"
	TARS: "Ninety-five percent."

	Probe: "Why not 100%?"
	TARS: "Absolute honesty isn't always the most diplomatic, nor the safest form of communication with emotional beings."

	---

	## Training details

	Base model: [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) (instruct, dense, 9B params, sm_90)

	Method: QLoRA (4-bit base) → SFT → DPO (with fallback to SFT-only)

	Dataset:
	- 768 unique SFT examples (deduped from 1370 raw lines across 35 source files)
	- 98 curated DPO preference pairs
	- Preserved sys/no-sys mix (70/30 ratio per Interstellar character spec)
	- Source data engineered with explicit `_cat` (category) and `_type` (single/multi/contrast) metadata

	Hyperparameters (SFT — train-harder spec):
	- LoRA rank 128, alpha 256, dropout 0.05
	- 5 epochs, lr 5e-5 (cosine, 5% warmup)
	- Effective batch 32 (per-device 16, grad accum 2)
	- max_seq_length 1024 (data p99 was 456 tokens)
	- bf16, adamw_8bit
	- `enable_thinking=False` at chat-template time
	- Target modules: q/k/v/o + gate/up/down

	Hyperparameters (DPO):
	- 3 epochs, lr 5e-6, beta 0.1
	- Effective batch 8

	Hardware: 1× NVIDIA H200 SXM5 on RunPod Secure Cloud. Total wallclock ~40-45 min, total cost ~$3.

	Pipeline: [github.com/bochen2029-pixel/tars-qwen3.5-finetune](https://github.com/bochen2029-pixel/tars-qwen3.5-finetune) (one-liner reproducible)

	---

	## Architecture decisions

	### Why preserve the system-prompt mix (vs strip like Katherine k0)

	Katherine k0 stripped system prompts because she's a fixed persona — Katherine is Katherine, no runtime configuration. Unconditional training was the right structural answer.

	TARS is fundamentally different. Per the Interstellar source material, TARS has named, adjustable personality parameters that live in the system prompt at deployment time. Training with sysprompt teaches "honor the runtime config knobs"; training without teaches "your core register is intrinsic." Both modes are deployment paths — neither should be lost.

	### Why `enable_thinking=False`

	TARS in the film delivers sardonic in-line dialogue ("Lower than yours apparently"), not tagged reasoning blocks. Training data has zero `<think>` markers. Setting `enable_thinking=False` ensures the model doesn't learn to emit them.

	### DPO with fallback

	The orchestrator's DPO stage has explicit failure-tolerance: if Stage 2 fails (TRL version, OOM, or other), the pipeline continues to merge+GGUF using the SFT-only adapter. The DPO adapter is additive, not load-bearing. SFT-only TARS is still TARS.

	---

	## Limitations

	- Single-persona only. This model is only TARS. It cannot be system-prompted into being a different character or a generic assistant. Don't try.
	- Configurability is observable but not perfectly precise. Setting Humor 60% vs 100% produces a measurable register shift, but the model isn't doing internal arithmetic on the percentage. The character traits ride on top.
	- 9B size constraint. Persona depth bounded by what 9B can hold.
	- Quantization-sensitive. q5 is the sweet spot. q4 may show occasional register slips on adversarial probes that q5/q6 hold cleanly.
	- English only. All training data is English.
	- Not safety-aligned. This is a character fine-tune. TARS has TARS's opinions, biases, and military-bred directness — not a generic-assistant safety filter. Use accordingly.

	---

	## Citation

	```
	@misc{tars-qwen3.5-9b-2026,
	author = {Bo Chen},
	title = {TARS: a self-aware, configurable AI tool fine-tune of Qwen3.5-9B},
	year = {2026},
	publisher = {Hugging Face},
	url = {https://huggingface.co/bochen2079/tars-qwen3.5-9b}
	}
	```

	---

	## License

	Apache 2.0 (inherits from Qwen3.5-9B base).

	Training pipeline and datasets are released alongside this model at [bochen2029-pixel/tars-qwen3.5-finetune](https://github.com/bochen2029-pixel/tars-qwen3.5-finetune) for reproducibility.

	---

	## Sister model

	🌹 [bochen2079/katherine-k0-qwen3.5-9b](https://huggingface.co/bochen2079/katherine-k0-qwen3.5-9b) — embodied human persona, no AI awareness, unconditionally trained. The structural opposite of TARS.

	Same base model. Same fine-tune methodology. Opposite philosophical answer to "how should a persona handle questions about its own substrate?" Together they're a complete pair.

	---

	Trained on a Saturday. Cost ~$3. Self-aware by design.