Instructions to use gaianet/MiniCPM-V-2_6-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gaianet/MiniCPM-V-2_6-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="gaianet/MiniCPM-V-2_6-GGUF",
	filename="MiniCPM-V-2_6-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use gaianet/MiniCPM-V-2_6-GGUF 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 gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf gaianet/MiniCPM-V-2_6-GGUF: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 gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf gaianet/MiniCPM-V-2_6-GGUF: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 gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M

Use Docker

docker model run hf.co/gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use gaianet/MiniCPM-V-2_6-GGUF with Ollama:
```
ollama run hf.co/gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M
```

Unsloth Studio

How to use gaianet/MiniCPM-V-2_6-GGUF 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 gaianet/MiniCPM-V-2_6-GGUF 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 gaianet/MiniCPM-V-2_6-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for gaianet/MiniCPM-V-2_6-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use gaianet/MiniCPM-V-2_6-GGUF with Docker Model Runner:
```
docker model run hf.co/gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M
```

Lemonade

How to use gaianet/MiniCPM-V-2_6-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull gaianet/MiniCPM-V-2_6-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM-V-2_6-GGUF-Q4_K_M

List all available models

lemonade list

MiniCPM-V-2_6-GGUF / config.json

apepkuss79

Upload config.json with huggingface_hub

aeda0c6 verified almost 2 years ago

Raw

History Blame Contribute Delete

1.6 kB

	{
	"_name_or_path": "/data1/sam/models/MiniCPM-V-2_6",
	"architectures": [
	"Qwen2ForCausalLM"
	],
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_minicpm.MiniCPMVConfig",
	"AutoModel": "modeling_minicpm.MiniCPMModel",
	"AutoModelForCausalLM": "modeling_minicpm.MiniCPMForCausalLM",
	"AutoModelForSeq2SeqLM": "modeling_minicpm.MiniCPMForCausalLM",
	"AutoModelForSequenceClassification": "modeling_minicpm.MiniCPMForSequenceClassification"
	},
	"batch_vision_input": true,
	"bos_token_id": 151643,
	"drop_vision_last_layer": false,
	"eos_token_id": 151645,
	"hidden_act": "silu",
	"hidden_size": 3584,
	"image_size": 448,
	"initializer_range": 0.02,
	"intermediate_size": 18944,
	"max_position_embeddings": 32768,
	"max_window_layers": 28,
	"model_type": "minicpmv",
	"num_attention_heads": 28,
	"num_hidden_layers": 28,
	"num_key_value_heads": 4,
	"patch_size": 14,
	"query_num": 64,
	"rms_norm_eps": 1e-06,
	"rope_theta": 1000000.0,
	"slice_config": {
	"max_slice_nums": 9,
	"model_type": "minicpmv"
	},
	"slice_mode": true,
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.44.0",
	"use_cache": true,
	"use_image_id": true,
	"use_sliding_window": false,
	"version": 2.6,
	"vision_batch_size": 16,
	"vision_config": {
	"hidden_size": 1152,
	"image_size": 980,
	"intermediate_size": 4304,
	"model_type": "siglip_vision_model",
	"num_attention_heads": 16,
	"num_hidden_layers": 27,
	"patch_size": 14
	},
	"vocab_size": 151666
	}