Instructions to use Mintzs/thinklite-draft-LHM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mintzs/thinklite-draft-LHM with Transformers:

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

pipe = pipeline("image-text-to-text", model="Mintzs/thinklite-draft-LHM")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Mintzs/thinklite-draft-LHM")
model = AutoModelForMultimodalLM.from_pretrained("Mintzs/thinklite-draft-LHM", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Mintzs/thinklite-draft-LHM 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 Mintzs/thinklite-draft-LHM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mintzs/thinklite-draft-LHM:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Mintzs/thinklite-draft-LHM:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mintzs/thinklite-draft-LHM:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf Mintzs/thinklite-draft-LHM:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf Mintzs/thinklite-draft-LHM:Q4_K_M

Use Docker

docker model run hf.co/Mintzs/thinklite-draft-LHM:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use Mintzs/thinklite-draft-LHM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mintzs/thinklite-draft-LHM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mintzs/thinklite-draft-LHM",
		"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/Mintzs/thinklite-draft-LHM:Q4_K_M

SGLang

How to use Mintzs/thinklite-draft-LHM 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 "Mintzs/thinklite-draft-LHM" \
    --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": "Mintzs/thinklite-draft-LHM",
		"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 "Mintzs/thinklite-draft-LHM" \
        --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": "Mintzs/thinklite-draft-LHM",
		"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 Mintzs/thinklite-draft-LHM with Ollama:
```
ollama run hf.co/Mintzs/thinklite-draft-LHM:Q4_K_M
```
Unsloth Desktop

How to use Mintzs/thinklite-draft-LHM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mintzs/thinklite-draft-LHM:Q4_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": "Mintzs/thinklite-draft-LHM:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Mintzs/thinklite-draft-LHM with Docker Model Runner:
```
docker model run hf.co/Mintzs/thinklite-draft-LHM:Q4_K_M
```

Lemonade

How to use Mintzs/thinklite-draft-LHM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mintzs/thinklite-draft-LHM:Q4_K_M

Run and chat with the model

lemonade run user.thinklite-draft-LHM-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Mintzs/thinklite-draft-LHM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mintzs/thinklite-draft-LHM: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 Mintzs/thinklite-draft-LHM:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Mintzs/thinklite-draft-LHM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Mintzs/thinklite-draft-LHM: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 "Mintzs/thinklite-draft-LHM: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"

Mintzs commited on 12 days ago

Commit

22776cd

verified ·

1 Parent(s): f8aed70

main: model card (BFCL label)

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -119,7 +119,7 @@ base model on hard problems. Thinklite-27B Max applies the full update.
 - **MMLU-Pro**: 1,000-question stratified subset
 - **IFEval**: 541 prompts, prompt-level strict
 - **LiveCodeBench v6**: 131 problems (2025-02 to 2025-04), pass@1
-- **BFCL v4**: 1,240 non-live function-calling cases
 ### Accuracy (%)
@@ -130,7 +130,7 @@ base model on hard problems. Thinklite-27B Max applies the full update.
 | MMLU-Pro | 86.3 | 84.4 | 84.7 | 84.7 | 82.6 |
 | IFEval | 91.1 | 86.3 | 84.3 | 83.9 | 83.0 |
 | LiveCodeBench v6 | 84.0 | 71.8 | 72.5 | 67.2 | 61.8 |
-| BFCL v4 | 88.7 | 90.8 | 90.4 | 90.4 | 90.2 |
 | **Average** | | **86.8** | **86.2** | **83.6** | **79.9** |
 ### Reasoning tokens per answer (mean; change vs Qwen3.8-27B at low)
@@ -142,7 +142,7 @@ base model on hard problems. Thinklite-27B Max applies the full update.
 | MMLU-Pro | 1,103 | 934 (-15%) | 748 (-32%) | 554 (-50%) |
 | IFEval | 659 | 464 (-30%) | 416 (-37%) | 326 (-51%) |
 | LiveCodeBench v6 | 10,741 | 9,152 (-15%) | 7,581 (-29%) | 5,639 (-48%) |
-| BFCL v4 | 96 | 80 (-17%) | 76 (-21%) | 70 (-27%) |
 | **All output tokens, 4,291 requests** | 4,915,895 | 4,244,014 (-14%) | 3,915,800 (-20%) | 3,285,976 (-33%) |
 ### Time to full answer, single user (seconds, median / p95; speed-up at the median)
@@ -154,7 +154,7 @@ base model on hard problems. Thinklite-27B Max applies the full update.
 | MMLU-Pro | 28.9 / 169 | 25.4 / 118 (14% faster) | 24.3 / 88 (19% faster) | 20.9 / 68 (38% faster) |
 | IFEval | 25.1 / 110 | 19.3 / 85 (30% faster) | 18.9 / 80 (33% faster) | 15.8 / 69 (59% faster) |
 | LiveCodeBench v6 | 129.4 / 1764 | 125.0 / 1588 (4% faster) | 89.4 / 1542 (45% faster) | 67.6 / 1323 (91% faster) |
-| BFCL v4 | 5.6 / 19 | 5.4 / 17 (4% faster) | 5.4 / 16 (4% faster) | 5.4 / 16 (4% faster) |
 TTFA is computed from each answer's length, the prompt prefill time and the single-user decode speed measured on the
 same GPU (about 28 tokens/s for every model). Thinklite-27B Low was timed in a separate run on the same GPU type; its

 - **MMLU-Pro**: 1,000-question stratified subset
 - **IFEval**: 541 prompts, prompt-level strict
 - **LiveCodeBench v6**: 131 problems (2025-02 to 2025-04), pass@1
+- **BFCL**: 1,240 non-live function-calling cases (BFCL v3 categories, official AST checker)
 ### Accuracy (%)
 | MMLU-Pro | 86.3 | 84.4 | 84.7 | 84.7 | 82.6 |
 | IFEval | 91.1 | 86.3 | 84.3 | 83.9 | 83.0 |
 | LiveCodeBench v6 | 84.0 | 71.8 | 72.5 | 67.2 | 61.8 |
+| BFCL | 88.7 | 90.8 | 90.4 | 90.4 | 90.2 |
 | **Average** | | **86.8** | **86.2** | **83.6** | **79.9** |
 ### Reasoning tokens per answer (mean; change vs Qwen3.8-27B at low)
 | MMLU-Pro | 1,103 | 934 (-15%) | 748 (-32%) | 554 (-50%) |
 | IFEval | 659 | 464 (-30%) | 416 (-37%) | 326 (-51%) |
 | LiveCodeBench v6 | 10,741 | 9,152 (-15%) | 7,581 (-29%) | 5,639 (-48%) |
+| BFCL | 96 | 80 (-17%) | 76 (-21%) | 70 (-27%) |
 | **All output tokens, 4,291 requests** | 4,915,895 | 4,244,014 (-14%) | 3,915,800 (-20%) | 3,285,976 (-33%) |
 ### Time to full answer, single user (seconds, median / p95; speed-up at the median)
 | MMLU-Pro | 28.9 / 169 | 25.4 / 118 (14% faster) | 24.3 / 88 (19% faster) | 20.9 / 68 (38% faster) |
 | IFEval | 25.1 / 110 | 19.3 / 85 (30% faster) | 18.9 / 80 (33% faster) | 15.8 / 69 (59% faster) |
 | LiveCodeBench v6 | 129.4 / 1764 | 125.0 / 1588 (4% faster) | 89.4 / 1542 (45% faster) | 67.6 / 1323 (91% faster) |
+| BFCL | 5.6 / 19 | 5.4 / 17 (4% faster) | 5.4 / 16 (4% faster) | 5.4 / 16 (4% faster) |
 TTFA is computed from each answer's length, the prompt prefill time and the single-user decode speed measured on the
 same GPU (about 28 tokens/s for every model). Thinklite-27B Low was timed in a separate run on the same GPU type; its