Instructions to use simpledirect/flash-1-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use simpledirect/flash-1-mini with Transformers:

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

pipe = pipeline("image-text-to-text", model="simpledirect/flash-1-mini")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("simpledirect/flash-1-mini")
model = AutoModelForMultimodalLM.from_pretrained("simpledirect/flash-1-mini")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use simpledirect/flash-1-mini with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="simpledirect/flash-1-mini",
	filename="gguf/flash-1-mini-20260602-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use simpledirect/flash-1-mini with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf simpledirect/flash-1-mini:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf simpledirect/flash-1-mini:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf simpledirect/flash-1-mini:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf simpledirect/flash-1-mini: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 simpledirect/flash-1-mini:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf simpledirect/flash-1-mini: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 simpledirect/flash-1-mini:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf simpledirect/flash-1-mini:Q4_K_M

Use Docker

docker model run hf.co/simpledirect/flash-1-mini:Q4_K_M

LM Studio
Jan

vLLM

How to use simpledirect/flash-1-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "simpledirect/flash-1-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "simpledirect/flash-1-mini",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/simpledirect/flash-1-mini:Q4_K_M

SGLang

How to use simpledirect/flash-1-mini 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 "simpledirect/flash-1-mini" \
    --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": "simpledirect/flash-1-mini",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "simpledirect/flash-1-mini" \
        --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": "simpledirect/flash-1-mini",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use simpledirect/flash-1-mini with Ollama:
```
ollama run hf.co/simpledirect/flash-1-mini:Q4_K_M
```

Unsloth Studio

How to use simpledirect/flash-1-mini 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 simpledirect/flash-1-mini 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 simpledirect/flash-1-mini to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for simpledirect/flash-1-mini to start chatting

How to use simpledirect/flash-1-mini with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf simpledirect/flash-1-mini: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": "simpledirect/flash-1-mini:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use simpledirect/flash-1-mini with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf simpledirect/flash-1-mini: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 simpledirect/flash-1-mini:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use simpledirect/flash-1-mini with Docker Model Runner:
```
docker model run hf.co/simpledirect/flash-1-mini:Q4_K_M
```

Lemonade

How to use simpledirect/flash-1-mini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull simpledirect/flash-1-mini:Q4_K_M

Run and chat with the model

lemonade run user.flash-1-mini-Q4_K_M

List all available models

lemonade list

Ayushnaik commited on 10 days ago

Commit

35550df

verified ·

1 Parent(s): 0b99b16

Finalize card: correct legal entity (Alpine Pacific Trading Inc.) + review fixes

Browse files

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ tags:
 flash-1-mini is a 4-billion-parameter model fine-tuned from Qwen3.5-4B for Canadian legal tasks. It is built for the parts of legal work that have to be right: producing correctly-formatted legal citations and following detailed instructions, across both of Canada's official languages and both of its legal traditions (common law and Quebec civil law). It retains the full general-reasoning and vision capability of its base model.
 - **Version:** `flash-1-mini-20260602`
-- **Developed by:** SimpleDirect Inc.
 - **Base model:** Qwen3.5-4B (Apache-2.0)
 - **License:** Apache-2.0
 - **Languages:** English, Canadian French
@@ -47,7 +47,7 @@ flash-1-mini is a 4-billion-parameter model fine-tuned from Qwen3.5-4B for Canad
 Measured against its base model under identical conditions (same prompts, same scoring):
 - **2.7× more reliable legal citations** — citation-integrity accuracy 42.1% vs 15.8% on the CBLRE benchmark.
-- **+23 points on instruction-following** — IFEval prompt-strict 53.2% vs 30.3%.
 - **Balanced bilingual competence** — privacy-compliance parity ratio of 1.00 (English 90.9% / French 90.9%).
 - **Stronger English legal reasoning** — MMLU international law 76.0% vs 70.3%.
 - **No loss of general capability** — MMLU unchanged (~69.8%); complex multi-step reasoning improves (BBH 79.0% vs 68.6%).
@@ -104,7 +104,7 @@ When serving via vLLM, pass `--reasoning-parser qwen3`; to disable thinking per
 ### Serving
-The model serves with **vLLM** for production text and multimodal inference (Transformers ≥ 5.5). Greedy decoding (temperature 0) is recommended for legal tasks where determinism matters. For text-only workloads, vLLM's `--language-model-only` flag skips the vision encoder to free memory for additional KV cache.
 ### Quantized / GGUF / Ollama
@@ -128,9 +128,10 @@ All figures are flash-1-mini vs the Qwen3.5-4B base under identical conditions (
 Specialization carried measurable costs, reported here in full:
-- **Retrieval (RAG):** source-attribution accuracy regressed (0.81 → 0.76 on a leak-proof held-out set). flash-1-mini is not a retrieval/RAG leader.
 - **Function-calling (BFCL v4):** overall regressed (37.7% → 28.6%), with multi-turn the weakest sub-category.
-- **French professional-law MCQ** and a few French-general tasks regressed modestly.
 If your workload is primarily retrieval-grounded QA or tool/function-calling orchestration, evaluate carefully against these numbers.
@@ -155,7 +156,7 @@ flash-1-mini is released under the **Apache License 2.0**. It is a modified deri
 ```bibtex
 @misc{simpledirect2026flash1mini,
   title  = {flash-1-mini: A Bilingual Canadian Legal Language Model},
-  author = {SimpleDirect Inc.},
   year   = {2026},
   note   = {Version flash-1-mini-20260602. Derivative of Qwen3.5-4B (Apache-2.0).},
   howpublished = {\url{https://huggingface.co/simpledirect/flash-1-mini}}

 flash-1-mini is a 4-billion-parameter model fine-tuned from Qwen3.5-4B for Canadian legal tasks. It is built for the parts of legal work that have to be right: producing correctly-formatted legal citations and following detailed instructions, across both of Canada's official languages and both of its legal traditions (common law and Quebec civil law). It retains the full general-reasoning and vision capability of its base model.
 - **Version:** `flash-1-mini-20260602`
+- **Developed by:** Alpine Pacific Trading Inc. (operating as SimpleDirect®)
 - **Base model:** Qwen3.5-4B (Apache-2.0)
 - **License:** Apache-2.0
 - **Languages:** English, Canadian French
 Measured against its base model under identical conditions (same prompts, same scoring):
 - **2.7× more reliable legal citations** — citation-integrity accuracy 42.1% vs 15.8% on the CBLRE benchmark.
+- **+22.9 points on instruction-following** — IFEval prompt-strict 53.2% vs 30.3%.
 - **Balanced bilingual competence** — privacy-compliance parity ratio of 1.00 (English 90.9% / French 90.9%).
 - **Stronger English legal reasoning** — MMLU international law 76.0% vs 70.3%.
 - **No loss of general capability** — MMLU unchanged (~69.8%); complex multi-step reasoning improves (BBH 79.0% vs 68.6%).
 ### Serving
+The model serves with **vLLM** for production text and multimodal inference (Transformers ≥ 5.5). Greedy decoding (temperature 0) is recommended for legal tasks where determinism matters.
 ### Quantized / GGUF / Ollama
 Specialization carried measurable costs, reported here in full:
+- **Retrieval (RAG):** source-attribution accuracy regressed (80.5% → 75.5% on a leak-proof held-out set). flash-1-mini is not a retrieval/RAG leader.
 - **Function-calling (BFCL v4):** overall regressed (37.7% → 28.6%), with multi-turn the weakest sub-category.
+- **French professional-law MCQ (Global-MMLU FR):** regressed (49.0% → 44.6%).
+- **CBLRE Quebec civil law:** regressed (95.0% → 90.0%).
 If your workload is primarily retrieval-grounded QA or tool/function-calling orchestration, evaluate carefully against these numbers.
 ```bibtex
 @misc{simpledirect2026flash1mini,
   title  = {flash-1-mini: A Bilingual Canadian Legal Language Model},
+  author = {{Alpine Pacific Trading Inc. (operating as SimpleDirect)}},
   year   = {2026},
   note   = {Version flash-1-mini-20260602. Derivative of Qwen3.5-4B (Apache-2.0).},
   howpublished = {\url{https://huggingface.co/simpledirect/flash-1-mini}}