Instructions to use faysalbenahmed/AMF-G1-4B-Experimental with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use faysalbenahmed/AMF-G1-4B-Experimental with Transformers:

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

pipe = pipeline("text-generation", model="faysalbenahmed/AMF-G1-4B-Experimental")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("faysalbenahmed/AMF-G1-4B-Experimental")
model = AutoModelForCausalLM.from_pretrained("faysalbenahmed/AMF-G1-4B-Experimental", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use faysalbenahmed/AMF-G1-4B-Experimental 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 faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M
# Run inference directly in the terminal:
llama cli -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_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 faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_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 faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M

Use Docker

docker model run hf.co/faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M

LM Studio
Jan

vLLM

How to use faysalbenahmed/AMF-G1-4B-Experimental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "faysalbenahmed/AMF-G1-4B-Experimental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "faysalbenahmed/AMF-G1-4B-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M

SGLang

How to use faysalbenahmed/AMF-G1-4B-Experimental 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 "faysalbenahmed/AMF-G1-4B-Experimental" \
    --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": "faysalbenahmed/AMF-G1-4B-Experimental",
		"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 "faysalbenahmed/AMF-G1-4B-Experimental" \
        --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": "faysalbenahmed/AMF-G1-4B-Experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use faysalbenahmed/AMF-G1-4B-Experimental with Ollama:
```
ollama run hf.co/faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M
```
Unsloth Desktop

How to use faysalbenahmed/AMF-G1-4B-Experimental with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M

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": "faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use faysalbenahmed/AMF-G1-4B-Experimental with Docker Model Runner:
```
docker model run hf.co/faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M
```

Lemonade

How to use faysalbenahmed/AMF-G1-4B-Experimental with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M

Run and chat with the model

lemonade run user.AMF-G1-4B-Experimental-Q5_K_M

List all available models

lemonade list

Hermes Agent

How to use faysalbenahmed/AMF-G1-4B-Experimental with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_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 faysalbenahmed/AMF-G1-4B-Experimental:Q5_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use faysalbenahmed/AMF-G1-4B-Experimental with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf faysalbenahmed/AMF-G1-4B-Experimental:Q5_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 "faysalbenahmed/AMF-G1-4B-Experimental:Q5_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"

AMF G1 — 4B Experimental

First learned neural artifact fabricated by AI Mission Foundry (AMF).

Created and developed by Fayçal Benahmed
Stack Moderne — France

G1 is not published as a qualified production model.
It is published as evidence of the AMF fabrication process that produced it.

Status

Property	Status
Learned AMF artifact physically created	YES
Parent lineage sealed	YES
Canonical cold reload	PASS
Local BF16 execution	PASS
GGUF Q5_K_M derivation	PASS
Local Q5 execution	PASS
Local deployment behavior gate	PASS — 15/15
Local runtime viable	YES
Full AMF optimization / REPAIR loop used	NO
Model capability qualified	NO
System qualified	NO
Production recommended	NO

What is G1?

G1 is the first learned neural model artifact produced during the AMF Model Foundry experiments.

Its exact upstream substrate is:

Qwen/Qwen3-4B-Instruct-2507
revision: cdbee75f17c01a7cc42f958dc650907174af0554

AMF applied:

supervised LoRA training
rank = 16
learning rate = 4e-5
steps = 72
seed = 190901
followed by a safe merge

The result is a materialized derived neural checkpoint.

Important experimental limitation

G1 was produced before the intended AMF autonomous optimization and REPAIR loop was correctly implemented.

RC1 effectively executed:

MEASURE
  -> IDENTIFY CAPABILITY GAP
  -> FABRICATE G1
  -> REMEASURE
  -> FAIL
  -> STOP

The intended Foundry loop is:

MEASURE
  -> DIAGNOSE
  -> FABRICATE / COMPOSE
  -> REMEASURE
  -> ANALYZE RESIDUAL FAILURE
  -> CHOOSE REPAIR LOCUS
  -> REPAIR
  -> REMEASURE
  -> repeat until PASS or justified refusal

Therefore G1 should be interpreted as:

the first fabricated candidate from an incomplete optimization loop,
not the final output of a completed AMF search.

Its measured failure is part of the research record.

Qualification result

The sealed G1 DEV measurement produced:

quality_state: FAIL_OBSERVED
qualified_output: 0.3472
latency_p95_s: 4.4042

Therefore:

MODEL_CAPABILITY_QUALIFIED = NO

AMF does not convert a failed qualification into a marketing PASS.

Known observed limitation

An original smoke test produced an exact-surface fidelity error:

evidence: Sarah Klein
output:   sarah klien

This observation contributed to the later design of evidence-grounded diagnosis and REPAIR.

Local deployment derivative

The canonical BF16 model was transported to a consumer laptop and executed locally under CPU-only inference.

A GGUF Q5_K_M derivative was then created.

Measured Q5 deployment:

parameters:             4.02B
model size:             2.69 GiB
CPU:                    AMD Ryzen 5 8540U
threads:                6
prompt throughput:      11.73 +/- 0.35 tokens/s
generation throughput:  5.68 +/- 1.17 tokens/s
peak RSS:               approximately 3.04 GiB
swap:                   0

Local execution:

G1_Q5_LOCAL_EXECUTION = PASS

Local behavior gate

A separate deployment-oriented micro-evaluation tested:

SUPPORTED_FACTS
MISSING_EVIDENCE
CONTRADICTION
STRICT_SCHEMA
EXACT_EVIDENCE_FIDELITY

Each probe was repeated three times.

Result:

exact passes:            15 / 15
exact pass rate:         1.000
exact evidence fidelity: PASS
local behavior gate:     PASS

This local gate is not the sealed AMF DEV/ROB/OOD qualification suite and does not change G1's qualification status.

The local gate also used a newly defined protocol rather than an exact replay of the historical A100 smoke prompts.

Artifact identity

Canonical G1 transport archive SHA256:

413ef141957d3dc4e3ec431a02bc37f4e02b0649c8d0cb61883de385ab86cb76

Internal G1 artifact SHA256:

9ee32a40e2aec3fe329fcef7f4c7fbe11444781c28fa14660d735df5ef7cebfa

GGUF Q5_K_M SHA256:

9cb29f9b6c1fffc6d8bf749c15f25b050c2c85569f5abfc7a888e099ea5e56a2

Training dataset receipt SHA256:

666462534451178582d29eb2214697bc9dbc1598bcf27b843b438f64ee2f0182

The available RC1 dataset receipt records:

split = train
final_access = NONE

The archived receipt does not contain a fuller textual provenance statement, so this release does not make additional claims about dataset provenance.

Why publish G1?

G1 is not presented as a state-of-the-art model.

It records a concrete transition in AMF research:

existing intelligence
  -> capability measurement
  -> identified gap
  -> learned fabrication
  -> materialized model
  -> measured failure
  -> local deployment transformation
  -> evidence for future REPAIR

Its failure is deliberately preserved.

AMF Agent is a separate public artifact demonstrating a system that passed its defined qualification gates.

G1 demonstrates that AMF can also fabricate learned neural material.

AMF

AI Mission Foundry

Mission + Constraints
        |
        v
       AMF
        |
        v
Qualified Intelligence Fabric
    or qualified refusal

AMF treats models as raw material, capabilities as qualified components, and systems as architectures engineered for a mission.

Attribution

AMF — AI Mission Foundry
Created and developed by Fayçal Benahmed
Independent research and engineering project
https://stack-moderne.fr/

License

G1 is derived from Qwen/Qwen3-4B-Instruct-2507, which is distributed under the Apache License 2.0.

Third-party software and components remain governed by their respective licenses.

Downloads last month: 162

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for faysalbenahmed/AMF-G1-4B-Experimental

Base model

Qwen/Qwen3-4B-Instruct-2507

Quantized

(303)

this model

Quantizations

1 model