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

7975cfa

verified ·

1 Parent(s): 433c92d

Add EVAL_RESULTS.md

Browse files

Files changed (1) hide show

EVAL_RESULTS.md +52 -0

EVAL_RESULTS.md ADDED Viewed

	@@ -0,0 +1,52 @@

+# FlowX Semantic Mapper (4B) — Evaluation Results
+Held-out evaluation of the released model (`flowx-semantic-mapper-4b-v2`). All numbers are on a
+**document-disjoint held-out set of 112 records** spanning EN/FR/DE/RO across banking,
+insurance, logistics, and labor. Decoding: greedy (temperature 0), `enable_thinking=False`.
+Metrics are exact set-match precision/recall/F1 unless noted; `concepts` also reports a
+fuzzy/semantic token-match F1, and `entities` reports field-accuracy over actor/action/object.
+## Headline (held-out, n=112)
+| Field | Precision | Recall | F1 |
+| --- | --- | --- | --- |
+| JSON validity | | | 1.00 |
+| all-3-facets present | | | 1.00 |
+| domain_tags (free-text) | 0.552 | 0.570 | 0.555 |
+| concepts (controlled 252-vocab, exact) | 0.547 | 0.558 | 0.541 |
+| concepts (fuzzy / semantic match) | 0.596 | 0.590 | 0.578 |
+| entities (field-accuracy) | | | 0.530 |
+## The controlled-vocabulary result (before / after)
+The central design change of this release was replacing open free-text `concepts` (1062
+unique labels, 88% seen exactly once, unlearnable and unmeasurable) with a **controlled
+252-concept taxonomy** (`concept_taxonomy.yaml`), then expanding the corpus with real
+regulatory text.
+| Concepts F1 | value | held-out |
+| --- | --- | --- |
+| open free-text vocabulary (v1) | 0.24 (exact) / 0.37 (fuzzy) | n=35 |
+| controlled vocab + data expansion (this release) | **0.54** (exact) / **0.58** (fuzzy) | n=112 |
+Concepts F1 more than doubled, and `entities` went from **unmeasurable** (the facet was empty
+in the old held-out) to **0.53**, on a held-out set that is 3x larger and multilingual.
+## Honest reading / caveats
+- **Home-field note.** The held-out shares the annotation lineage of the training data
+  (real regulatory text, frontier-model-assisted ontology annotation to the controlled vocab).
+  Read these as a strong format-and-consistency signal; validate on your own corpus before
+  production claims.
+- **Concepts are partial (~0.54).** The model surfaces many but not all applicable concepts.
+- **`domain_tags` are free-text on purpose** (recall + human browsing) and are honestly noisier
+  than the controlled `concepts`.
+- **English is strongest;** FR/DE/RO are supported and materially improved by the real-data
+  expansion, but remain a bit weaker than EN.
+## Reproduction
+Held-out set: `mlx_data/ontology_cv2/valid.jsonl` (built document-disjoint from the training
+split). Scorer: `eval_mapper_4b.py <model_path> mlx_data/ontology_cv2/valid.jsonl`.
+_Author: Bogdan Răduță, Head of Research, FlowX.AI._