Instructions to use OsaurusAI/MiniMax-M2.7-JANGTQ_K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/MiniMax-M2.7-JANGTQ_K with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("OsaurusAI/MiniMax-M2.7-JANGTQ_K")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

Pi new

How to use OsaurusAI/MiniMax-M2.7-JANGTQ_K with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/MiniMax-M2.7-JANGTQ_K"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "OsaurusAI/MiniMax-M2.7-JANGTQ_K"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/MiniMax-M2.7-JANGTQ_K with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/MiniMax-M2.7-JANGTQ_K"

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 OsaurusAI/MiniMax-M2.7-JANGTQ_K

Run Hermes

hermes

MLX LM

How to use OsaurusAI/MiniMax-M2.7-JANGTQ_K with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OsaurusAI/MiniMax-M2.7-JANGTQ_K"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/MiniMax-M2.7-JANGTQ_K"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/MiniMax-M2.7-JANGTQ_K",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

MiniMax-M2.7-JANGTQ_K / config.json

Osaurus-AI

Upload config.json with huggingface_hub

8716d6a verified 23 days ago

raw

history blame contribute delete

2.12 kB

	{
	"architectures": [
	"MiniMaxM2ForCausalLM"
	],
	"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"
	},
	"dtype": "bfloat16",
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"intermediate_size": 1536,
	"max_position_embeddings": 196608,
	"model_type": "minimax_m2",
	"mtp_transformer_layers": 0,
	"num_attention_heads": 48,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 62,
	"num_key_value_heads": 8,
	"num_local_experts": 256,
	"num_mtp_modules": 0,
	"qk_norm_type": "per_layer",
	"rms_norm_eps": 1e-06,
	"rope_theta": 5000000,
	"rotary_dim": 64,
	"scoring_func": "sigmoid",
	"shared_intermediate_size": 0,
	"tie_word_embeddings": false,
	"transformers_version": "4.46.1",
	"use_cache": true,
	"use_mtp": false,
	"use_qk_norm": true,
	"use_routing_bias": true,
	"vocab_size": 200064,
	"_name_or_path": "M2.5-SLURPY",
	"quantization": {
	"bits": 8,
	"mode": "affine",
	"group_size": 64,
	"routed_expert_bits": {
	"gate_proj": 2,
	"down_proj": 4,
	"up_proj": 2
	},
	"mxtq_bits": {
	"routed_expert": {
	"gate_proj": 2,
	"down_proj": 4,
	"up_proj": 2
	},
	"attention": 8,
	"shared_expert": 8,
	"embed_tokens": 8,
	"lm_head": 8,
	"norms_router_biases": 16
	}
	},
	"mxtq_bits": {
	"routed_expert": {
	"gate_proj": 2,
	"down_proj": 4,
	"up_proj": 2
	},
	"attention": 8,
	"shared_expert": 8,
	"embed_tokens": 8,
	"lm_head": 8,
	"norms_router_biases": 16
	},
	"weight_format": "mxtq"
	}