Instructions to use prithivMLmods/Holo4-27B-MTP-Repacked with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Holo4-27B-MTP-Repacked with Transformers:

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

pipe = pipeline("image-text-to-text", model="prithivMLmods/Holo4-27B-MTP-Repacked")
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("prithivMLmods/Holo4-27B-MTP-Repacked")
model = AutoModelForMultimodalLM.from_pretrained("prithivMLmods/Holo4-27B-MTP-Repacked", 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 prithivMLmods/Holo4-27B-MTP-Repacked 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 prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Holo4-27B-MTP-Repacked: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 prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use prithivMLmods/Holo4-27B-MTP-Repacked with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Holo4-27B-MTP-Repacked"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Holo4-27B-MTP-Repacked",
		"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/prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M

SGLang

How to use prithivMLmods/Holo4-27B-MTP-Repacked 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 "prithivMLmods/Holo4-27B-MTP-Repacked" \
    --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": "prithivMLmods/Holo4-27B-MTP-Repacked",
		"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 "prithivMLmods/Holo4-27B-MTP-Repacked" \
        --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": "prithivMLmods/Holo4-27B-MTP-Repacked",
		"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 prithivMLmods/Holo4-27B-MTP-Repacked with Ollama:
```
ollama run hf.co/prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M
```
Unsloth Desktop

How to use prithivMLmods/Holo4-27B-MTP-Repacked with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Holo4-27B-MTP-Repacked: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": "prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use prithivMLmods/Holo4-27B-MTP-Repacked with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M
```

Lemonade

How to use prithivMLmods/Holo4-27B-MTP-Repacked with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M

Run and chat with the model

lemonade run user.Holo4-27B-MTP-Repacked-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use prithivMLmods/Holo4-27B-MTP-Repacked with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Holo4-27B-MTP-Repacked: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 prithivMLmods/Holo4-27B-MTP-Repacked:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use prithivMLmods/Holo4-27B-MTP-Repacked with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf prithivMLmods/Holo4-27B-MTP-Repacked: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 "prithivMLmods/Holo4-27B-MTP-Repacked: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"

prithivMLmods commited on 1 day ago

Commit

730b71c

verified ·

1 Parent(s): 0176659

Update README.md

Browse files

Files changed (1) hide show

README.md +23 -1

README.md CHANGED Viewed

@@ -2,4 +2,26 @@
 license: apache-2.0
 base_model:
 - Hcompany/Holo4-27B
----

 license: apache-2.0
 base_model:
 - Hcompany/Holo4-27B
+library_name: transformers
+---
+## MTP-Repacked [Transformers, BF16]
+| File Name | File Type | File Size | File Link | Description |
+|-----------|-----------|-----------|-----------|-------------|
+| chat_template.jinja | Jinja Template | 8.95 kB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/chat_template.jinja) | Chat template for formatting conversations and prompts. |
+| config.json | JSON | 3.72 kB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/config.json) | Core model architecture and configuration parameters. |
+| generation_config.json | JSON | 213 Bytes | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/generation_config.json) | Default text generation parameters (e.g., temperature, top_p). |
+| merges.txt | Text | 3.35 MB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/merges.txt) | Byte-Pair Encoding (BPE) merge rules for the tokenizer. |
+| model-00001-of-00006.safetensors | Safetensors | 10.9 GB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/model-00001-of-00006.safetensors) | Model weight shard 1/6. **Required** to load the model. |
+| model-00002-of-00006.safetensors | Safetensors | 11 GB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/model-00002-of-00006.safetensors) | Model weight shard 2/6. **Required** to load the model. |
+| model-00003-of-00006.safetensors | Safetensors | 10.9 GB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/model-00003-of-00006.safetensors) | Model weight shard 3/6. **Required** to load the model. |
+| model-00004-of-00006.safetensors | Safetensors | 10.8 GB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/model-00004-of-00006.safetensors) | Model weight shard 4/6. **Required** to load the model. |
+| model-00005-of-00006.safetensors | Safetensors | 8.54 GB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/model-00005-of-00006.safetensors) | Model weight shard 5/6. **Required** to load the model. |
+| model-00006-of-00006.safetensors | Safetensors | 3.39 GB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/model-00006-of-00006.safetensors) | Model weight shard 6/6. **Required** to load the model. |
+| model.safetensors.index.json | JSON | 112 kB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/model.safetensors.index.json) | Index file mapping model weights to their respective shards. |
+| preprocessor_config.json | JSON | 390 Bytes | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/preprocessor_config.json) | Configuration for preprocessing vision/image inputs. |
+| tokenizer.json | JSON | 12.8 MB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/tokenizer.json) | Complete tokenizer vocabulary and encoding rules. |
+| tokenizer_config.json | JSON | 17.9 kB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/tokenizer_config.json) | Tokenizer-specific configuration parameters. |
+| video_preprocessor_config.json | JSON | 385 Bytes | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/video_preprocessor_config.json) | Configuration for preprocessing video inputs. |
+| vocab.json | JSON | 6.72 MB | [Link](https://huggingface.co/prithivMLmods/Holo4-27B-MTP-Repacked/blob/main/vocab.json) | Tokenizer vocabulary mapping tokens to IDs. |