Instructions to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE",
	filename="gguf/MiniMax-2.7-LegalReapV2Adaptive-BASE.Q8_0.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 ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE 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 ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0
# Run inference directly in the terminal:
llama cli -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0
# Run inference directly in the terminal:
llama cli -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

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 ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

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 ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

Use Docker

docker model run hf.co/ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

LM Studio
Jan
Ollama
How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with Ollama:
```
ollama run hf.co/ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0
```

Unsloth Studio

How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE 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 ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE 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 ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE to start chatting

How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

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": "ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

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 ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

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 "ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0" \
  --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"

Docker Model Runner
How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with Docker Model Runner:
```
docker model run hf.co/ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0
```

Lemonade

How to use ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ProprietaryLegal/MiniMax-2.7-LegalReapV2Adaptive-BASE:Q8_0

Run and chat with the model

lemonade run user.MiniMax-2.7-LegalReapV2Adaptive-BASE-Q8_0

List all available models

lemonade list

MiniMax-2.7-LegalReapV2Adaptive-BASE / config.json

ProprietaryLegal

Pruned bf16 checkpoint (adaptive REAP 0.35, per-layer 116-198/256)

c0ee9d7 verified 4 days ago

Raw

History Blame Contribute Delete

2.69 kB

	{
	"architectures": [
	"MiniMaxM2ForCausalLM"
	],
	"attention_dropout": 0.0,
	"attn_type_list": [
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1,
	1
	],
	"auto_map": {
	"AutoConfig": "configuration_minimax_m2.MiniMaxM2Config",
	"AutoModelForCausalLM": "modeling_minimax_m2.MiniMaxM2ForCausalLM"
	},
	"bos_token_id": 1,
	"dtype": "bfloat16",
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 1536,
	"max_position_embeddings": 204800,
	"model_type": "minimax_m2",
	"mtp_transformer_layers": 1,
	"num_attention_heads": 48,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 62,
	"num_key_value_heads": 8,
	"num_local_experts": 198,
	"num_mtp_modules": 3,
	"output_router_logits": false,
	"partial_rotary_factor": 0.5,
	"qk_norm_type": "per_layer",
	"reap_adaptive_nonuniform_experts": true,
	"reap_adaptive_retained_experts_by_layer": {
	"0": 116,
	"1": 144,
	"10": 197,
	"11": 197,
	"12": 196,
	"13": 198,
	"14": 196,
	"15": 196,
	"16": 194,
	"17": 198,
	"18": 195,
	"19": 191,
	"2": 164,
	"20": 186,
	"21": 192,
	"22": 189,
	"23": 187,
	"24": 180,
	"25": 182,
	"26": 177,
	"27": 173,
	"28": 170,
	"29": 170,
	"3": 180,
	"30": 168,
	"31": 163,
	"32": 162,
	"33": 157,
	"34": 157,
	"35": 162,
	"36": 164,
	"37": 162,
	"38": 161,
	"39": 155,
	"4": 194,
	"40": 167,
	"41": 149,
	"42": 155,
	"43": 155,
	"44": 160,
	"45": 158,
	"46": 156,
	"47": 159,
	"48": 155,
	"49": 152,
	"5": 190,
	"50": 148,
	"51": 146,
	"52": 140,
	"53": 137,
	"54": 139,
	"55": 141,
	"56": 139,
	"57": 136,
	"58": 138,
	"59": 133,
	"6": 190,
	"60": 124,
	"61": 116,
	"7": 187,
	"8": 188,
	"9": 186
	},
	"rms_norm_eps": 1e-06,
	"rope_theta": 5000000,
	"rotary_dim": 64,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"scoring_func": "sigmoid",
	"shared_intermediate_size": 0,
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.55.0",
	"use_cache": false,
	"use_mtp": true,
	"use_qk_norm": true,
	"use_routing_bias": true,
	"vocab_size": 200064
	}