Instructions to use lerugray/hammerstein-7b-framework with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lerugray/hammerstein-7b-framework with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-7B-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "lerugray/hammerstein-7b-framework")

llama-cpp-python

How to use lerugray/hammerstein-7b-framework with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lerugray/hammerstein-7b-framework",
	filename="Qwen2.5-7B-Instruct.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use lerugray/hammerstein-7b-framework 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 lerugray/hammerstein-7b-framework:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lerugray/hammerstein-7b-framework:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf lerugray/hammerstein-7b-framework:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lerugray/hammerstein-7b-framework: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 lerugray/hammerstein-7b-framework:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lerugray/hammerstein-7b-framework: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 lerugray/hammerstein-7b-framework:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lerugray/hammerstein-7b-framework:Q4_K_M

Use Docker

docker model run hf.co/lerugray/hammerstein-7b-framework:Q4_K_M

LM Studio
Jan

vLLM

How to use lerugray/hammerstein-7b-framework with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lerugray/hammerstein-7b-framework"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lerugray/hammerstein-7b-framework",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lerugray/hammerstein-7b-framework:Q4_K_M

Ollama
How to use lerugray/hammerstein-7b-framework with Ollama:
```
ollama run hf.co/lerugray/hammerstein-7b-framework:Q4_K_M
```

Unsloth Studio

How to use lerugray/hammerstein-7b-framework 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 lerugray/hammerstein-7b-framework 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 lerugray/hammerstein-7b-framework to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lerugray/hammerstein-7b-framework to start chatting

How to use lerugray/hammerstein-7b-framework with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lerugray/hammerstein-7b-framework: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": "lerugray/hammerstein-7b-framework:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use lerugray/hammerstein-7b-framework with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lerugray/hammerstein-7b-framework: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 lerugray/hammerstein-7b-framework:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use lerugray/hammerstein-7b-framework with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf lerugray/hammerstein-7b-framework: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 "lerugray/hammerstein-7b-framework: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"

Docker Model Runner
How to use lerugray/hammerstein-7b-framework with Docker Model Runner:
```
docker model run hf.co/lerugray/hammerstein-7b-framework:Q4_K_M
```

Lemonade

How to use lerugray/hammerstein-7b-framework with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lerugray/hammerstein-7b-framework:Q4_K_M

Run and chat with the model

lemonade run user.hammerstein-7b-framework-Q4_K_M

List all available models

lemonade list

hammerstein-7b-framework / README.md

lerugray

Restore full model card (the GGUF push had overwritten it with the Unsloth stub)

001f5d4 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

5.5 kB

	---
	base_model: unsloth/Qwen2.5-7B-Instruct-bnb-4bit
	library_name: peft
	pipeline_tag: text-generation
	license: apache-2.0
	tags:
	- lora
	- qlora
	- sft
	- unsloth
	- trl
	- hammerstein
	- strategic-reasoning
	- gguf
	- ollama
	---

	# Hammerstein-7B Framework — a small, opinionated strategic-reasoning model

	A QLoRA adapter on `Qwen2.5-7B-Instruct` that bakes the
	[Hammerstein framework](https://github.com/lerugray/hammerstein) into the
	weights via behavior cloning. Load base + adapter, run inference **with no
	system prompt at all**, and you get framework-correct strategic reasoning:
	it names which failure quadrant a plan sits in (clever-lazy /
	clever-industrious / stupid-industrious / stupid-lazy), pairs claims with
	counter-observations, and proposes structural fixes over discipline fixes.

	This is the framework-only public artifact (refreshed 2026-06-05). It is
	trained on a framework-corpus distillation with zero personal data — the
	training set was deterministically scrubbed and passed an adversarial
	multi-agent privacy sweep before release. (Ongoing personal-corpus
	fine-tuning of the author's daily-driver continues privately and is not
	published here.)

	## What it does that frontier assistants are tuned not to do

	The framework deliberately reinforces three behaviors the big labs train
	toward agreeableness and away from:

	- Refusal-with-pathway — when the right answer is "don't do this," it
	says so, and surfaces what would unblock a yes, instead of a flat no or
	a reluctant yes.
	- Hold-your-ground — it does not sycophantically fold when you push back
	with confidence but no new evidence. It restates the structural reason and
	tells you exactly what evidence would change its call.
	- Refuse stupid-industrious — it declines to validate a confidently-stated
	plan that works hard in the wrong direction; it names the quadrant and
	offers a verification gate + structural alternative.

	## Training data (framework-only, 1,994 pairs)

	\| Source \| Pairs \| What \|
	\|---\|---\|---\|
	\| Strategic (scrubbed v3a corpus) \| 1,708 \| audit-this-plan / scope-this-idea / is-this-worth-doing / what-should-we-do-next / review-from-different-angle, across 12 generic domains \|
	\| Unique-behavior reinforcement \| 72 \| the three doctrine behaviors above (24 each) \|
	\| Off-domain instruction-following \| 214 \| suppresses catastrophic forgetting (keeps general competence) \|

	Teacher: Qwen3.6-plus running the Hammerstein framework prompt (no corpus
	retrieval, neutralized persona — clean by construction). Behavior-cloning
	frame: no system prompt in the training targets — the framework is what
	the student learns to bake in.

	## Eval (framework-discipline benchmark, 2026-06-05)

	Structural framework-correctness on 40 held-out strategic prompts
	(higher = more framework-correct), and an out-of-domain forgetting check
	on 30 prompts (framework-vocab leakage into off-domain answers; lower =
	healthier):

	\| Condition \| Strategic (n=40) \| OOD leakage (n=30) \|
	\|---\|---\|---\|
	\| student (this adapter, no system prompt) \| 0.975 \| 0.000 \|
	\| ablation (base + framework system prompt) \| 0.675 \| 0.783 \|
	\| vanilla (base Qwen2.5-7B alone) \| 0.081 \| 0.000 \|

	**Adapter wins (Δ=+0.300 vs the prompt-only ablation) — the framework
	lives in the weights, not just a runtime prompt.** OOD leakage is 0.000:
	the distillation adds framework discipline with no measurable
	catastrophic forgetting. Note the prompt-only ablation actually leaks
	framework vocabulary into off-domain answers (0.783) where the distilled
	student does not — the student fires the framework when the task calls
	for it and stays quiet when it doesn't.

	The framework-fidelity axis is partly tautological (the rubric rewards
	framework vocabulary by design); the load-bearing signal is that the
	distillation carries the discipline into 7B weights with no runtime
	scaffolding, and does not wreck general competence (forgetting ≈ 0).

	## Usage

	```python
	from peft import PeftModel
	from transformers import AutoModelForCausalLM, AutoTokenizer

	base = "Qwen/Qwen2.5-7B-Instruct"
	tok = AutoTokenizer.from_pretrained(base)
	model = AutoModelForCausalLM.from_pretrained(base, device_map="auto")
	model = PeftModel.from_pretrained(model, "lerugray/hammerstein-7b-framework")

	msgs = [{"role": "user", "content": "Audit this plan: rewrite our API gateway from scratch in Rust to fix latency."}]
	ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
	print(tok.decode(model.generate(ids, max_new_tokens=600)[0][ids.shape[1]:], skip_special_tokens=True))
	```

	No system prompt needed. Runs locally on an 8 GB GPU at zero per-call cost.

	### Run it with Ollama (GGUF)

	A `Q4_K_M` GGUF (4.68 GB) and a `Modelfile` ship in this repo, so you can run it
	with no Python at all:

	```
	ollama run hf.co/lerugray/hammerstein-7b-framework:Q4_K_M
	```

	Or with llama.cpp directly: `llama-cli -hf lerugray/hammerstein-7b-framework --jinja`.

	## What this is not

	Not a general-purpose frontier replacement. It is tuned for framework-shaped
	strategic-reasoning tasks; generalization to neutral benchmarks (math, code,
	long-context) is untested. The framework is the IP; this adapter is the
	portability proof — a small owned model that holds an opinionated reasoning
	doctrine you can run yourself.

	Built alongside [hammerstein.ai](https://hammerstein.ai). Framework + corpus:
	[github.com/lerugray/hammerstein](https://github.com/lerugray/hammerstein).