Instructions to use flowxai/semantic-mapper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flowxai/semantic-mapper with Transformers:

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

pipe = pipeline("text-generation", model="flowxai/semantic-mapper")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flowxai/semantic-mapper")
model = AutoModelForCausalLM.from_pretrained("flowxai/semantic-mapper", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use flowxai/semantic-mapper with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("flowxai/semantic-mapper")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use flowxai/semantic-mapper 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 flowxai/semantic-mapper:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf flowxai/semantic-mapper:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf flowxai/semantic-mapper:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf flowxai/semantic-mapper: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 flowxai/semantic-mapper:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf flowxai/semantic-mapper: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 flowxai/semantic-mapper:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf flowxai/semantic-mapper:Q4_K_M

Use Docker

docker model run hf.co/flowxai/semantic-mapper:Q4_K_M

LM Studio
Jan

vLLM

How to use flowxai/semantic-mapper with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/flowxai/semantic-mapper:Q4_K_M

SGLang

How to use flowxai/semantic-mapper 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 "flowxai/semantic-mapper" \
    --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": "flowxai/semantic-mapper",
		"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 "flowxai/semantic-mapper" \
        --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": "flowxai/semantic-mapper",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use flowxai/semantic-mapper with Ollama:
```
ollama run hf.co/flowxai/semantic-mapper:Q4_K_M
```
Unsloth Desktop

How to use flowxai/semantic-mapper with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "flowxai/semantic-mapper"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "flowxai/semantic-mapper"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use flowxai/semantic-mapper with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "flowxai/semantic-mapper"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "flowxai/semantic-mapper"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "flowxai/semantic-mapper",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use flowxai/semantic-mapper with Docker Model Runner:
```
docker model run hf.co/flowxai/semantic-mapper:Q4_K_M
```

Lemonade

How to use flowxai/semantic-mapper with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull flowxai/semantic-mapper:Q4_K_M

Run and chat with the model

lemonade run user.semantic-mapper-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use flowxai/semantic-mapper with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "flowxai/semantic-mapper"

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 flowxai/semantic-mapper

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use flowxai/semantic-mapper with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "flowxai/semantic-mapper"

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 "flowxai/semantic-mapper" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

bogdanraduta commited on Jul 10

Commit

d5c6472

verified ·

1 Parent(s): 8196642

Add fp16 merged model (Qwen3-4B LoRA)

Browse files

Files changed (1) hide show

README.md +4 -110

README.md CHANGED Viewed

@@ -1,115 +1,9 @@
 ---
 license: apache-2.0
-language:
-  - en
-  - fr
-  - de
-  - ro
-base_model: Qwen/Qwen3-4B
-library_name: transformers
 pipeline_tag: text-generation
 tags:
-  - lora
-  - regulatory
-  - compliance
-  - ontology-extraction
-  - information-extraction
-  - mlx
-  - gguf
-  - flowx
 ---
-# FlowX Semantic Mapper (4B)
-**FlowX Semantic Mapper** reads a chunk of regulatory or legal text and emits a structured
-**ontology JSON** across three facets: **structural** (source hierarchy), **semantic**
-(domain tags, controlled-vocabulary concepts, and an actor/action/object/constraint entity),
-and **governance** (policy references, escalation trigger). It is a LoRA fine-tune of
-**Qwen3-4B**, built by FlowX.AI for regulated-industry NLP (banking, insurance, logistics,
-labor) in **English, French, German, and Romanian**.
-> Decision-support tool, **not legal advice**. Outputs should be reviewed by a qualified
-> professional before any compliance decision.
-## What it does
-Input: a regulatory text chunk. Output: JSON of the form
-```json
-{
-  "structural": {"source_id": "...", "hierarchy": ["...", "..."], "document_type": "..."},
-  "semantic": {
-    "domain_tags": ["insurance_regulation", "claims", "settlement"],
-    "concepts": ["claim_acknowledgement", "settlement_timeline"],
-    "entities": {"actor": "insurer", "action": "acknowledge claim communications",
-                 "object": "claim_communication", "constraint": {"condition": "reasonably_prompt"}}
-  },
-  "governance": {"policy_references": ["PDP.insurance.claims_settlement"],
-                 "escalation_trigger": "if !claim_acknowledged_promptly THEN escalate"}
-}
-```
-`concepts` are drawn from a **controlled 252-concept taxonomy** (`concept_taxonomy.yaml`,
-included), which is what makes them learnable, measurable, and consistent for downstream use.
-## Evaluation (held-out, n=112, multilingual)
-| Field | Precision | Recall | F1 |
-|---|---|---|---|
-| JSON validity | | | **100%** |
-| all-3-facets present | | | **100%** |
-| domain_tags | 0.55 | 0.57 | **0.55** |
-| concepts (controlled vocab) | 0.55 | 0.56 | **0.54** |
-| entities (field accuracy) | | | **0.53** |
-The controlled vocabulary plus a real-regulatory-text data expansion **more than doubled**
-concept F1 (0.24 open-vocab &rarr; 0.54 controlled) and made the entity facet measurable
-(0.00 &rarr; 0.53). Numbers are on a document-disjoint held-out spanning EN/FR/DE/RO.
-## Files & formats
-| Path | Format | Runs on |
-|---|---|---|
-| `/` (root) | fp16 safetensors (`transformers`) | CUDA / Linux servers, vLLM |
-| `mlx-int4/`, `mlx-int8/` | MLX quantized | Apple Silicon (on-device) |
-| `gguf/*.gguf` | GGUF Q8_0 / Q4_K_M | CUDA + CPU (llama.cpp / Ollama) |
-## Usage (transformers)
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-m = AutoModelForCausalLM.from_pretrained("flowxai/semantic-mapper", torch_dtype="auto", device_map="auto")
-tok = AutoTokenizer.from_pretrained("flowxai/semantic-mapper")
-msgs = [{"role": "system", "content": "You are a legal and regulatory ontology extractor.\nExtract structured tags from document chunks. Output ONLY valid JSON."},
-        {"role": "user", "content": "Extract ontology from this chunk:\n\nCHUNK:\n<your regulatory text>"}]
-ids = tok.apply_chat_template(msgs, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(m.device)
-print(tok.decode(m.generate(ids, max_new_tokens=1024)[0][ids.shape[1]:], skip_special_tokens=True))
-```
-(`enable_thinking=False` — the adapter was trained to emit pure JSON, no thinking block.)
-## Training
-LoRA (rank 32 / scale 16 / dropout 0.05), Qwen3-4B base, MLX-LM on Apple Silicon, ~3 epochs,
-cosine LR 1e-4&rarr;1e-5, max sequence length 2048. Data: **763 records** (651 train / 112
-held-out), document-disjoint. Composition: real, verbatim regulatory / legislative text from
-official public sources (US eCFR & state codes, EU EUR-Lex, France Legifrance, Germany
-Gesetze im Internet, Romania legislatie.just.ro, UNECE/ADR), annotated to the controlled
-252-concept taxonomy with frontier-model assistance and validated (concepts in-vocabulary,
-entities populated, source URL per record).
-## Limitations & responsible use
-- **Not legal advice** — a triage / structuring aid; always have important determinations
-  reviewed by a qualified professional.
-- Strongest in English; FR/DE/RO are supported but somewhat weaker (see per-language notes).
-- Concept extraction is partial (F1 ~0.54): it surfaces many but not all applicable concepts.
-- `domain_tags` are free-text and less consistent than the controlled `concepts`.
-## License & attribution
-Apache-2.0. Copyright 2026 FlowX.AI. See `NOTICE`. Base model: Qwen3-4B (Apache-2.0).
-Official legislation is reproduced with source acknowledgement (each training record carries
-its source URL).
-_Author: Bogdan Răduță, Head of Research, FlowX.AI._

 ---
+library_name: mlx
 license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE
 pipeline_tag: text-generation
+base_model: mlx-community/Qwen3-4B-4bit
 tags:
+- mlx
 ---