Instructions to use MemTensor/MemT-1.0-Nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MemTensor/MemT-1.0-Nano with Transformers:

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

pipe = pipeline("text-generation", model="MemTensor/MemT-1.0-Nano", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MemTensor/MemT-1.0-Nano", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MemTensor/MemT-1.0-Nano with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MemTensor/MemT-1.0-Nano"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MemTensor/MemT-1.0-Nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MemTensor/MemT-1.0-Nano

SGLang

How to use MemTensor/MemT-1.0-Nano 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 "MemTensor/MemT-1.0-Nano" \
    --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": "MemTensor/MemT-1.0-Nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MemTensor/MemT-1.0-Nano" \
        --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": "MemTensor/MemT-1.0-Nano",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MemTensor/MemT-1.0-Nano with Docker Model Runner:
```
docker model run hf.co/MemTensor/MemT-1.0-Nano
```

MemT-1.0-Nano / config.json

lulingoo

myturing

Upload model weights

b3655d7 4 days ago

Raw History Blame Contribute Delete

3.57 kB

{
  "model_type": "memt_qwen3_5_moe",
  "pad_token_id": 248044,
  "architectures": [
    "MemTQwen3_5MoeForCausalLM"
  ],
  "torch_dtype": "bfloat16",
  "tie_word_embeddings": false,
  "backbone_configs": {
    "model_type": "qwen3_5_moe",
    "text_config": {
      "attention_bias": false,
      "attention_dropout": 0.0,
      "attn_output_gate": true,
      "bos_token_id": 248044,
      "dtype": "bfloat16",
      "eos_token_id": 248044,
      "full_attention_interval": 4,
      "head_dim": 256,
      "hidden_act": "silu",
      "hidden_size": 2048,
      "initializer_range": 0.02,
      "layer_types": [
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention",
        "linear_attention",
        "linear_attention",
        "linear_attention",
        "full_attention"
      ],
      "linear_conv_kernel_dim": 4,
      "linear_key_head_dim": 128,
      "linear_num_key_heads": 16,
      "linear_num_value_heads": 32,
      "linear_value_head_dim": 128,
      "mamba_ssm_dtype": "float32",
      "max_position_embeddings": 262144,
      "model_type": "qwen3_5_moe_text",
      "moe_intermediate_size": 512,
      "mtp_num_hidden_layers": 1,
      "mtp_use_dedicated_embeddings": false,
      "num_attention_heads": 16,
      "num_experts": 256,
      "num_experts_per_tok": 8,
      "num_hidden_layers": 40,
      "num_key_value_heads": 2,
      "output_router_logits": false,
      "pad_token_id": null,
      "partial_rotary_factor": 0.25,
      "rms_norm_eps": 1e-06,
      "rope_parameters": {
        "mrope_interleaved": true,
        "mrope_section": [
          11,
          11,
          10
        ],
        "partial_rotary_factor": 0.25,
        "rope_theta": 10000000,
        "rope_type": "default"
      },
      "router_aux_loss_coef": 0.001,
      "shared_expert_intermediate_size": 512,
      "tie_word_embeddings": false,
      "use_cache": true,
      "vocab_size": 248320
    }
  },
  "memt": {
    "memory_update_mode": "token",
    "gdn_version": "stable_gdn2",
    "memory_use_short_conv": false,
    "memory_head_mode": "mha",
    "memory_read_scale": "k_inv_sqrt",
    "num_memory_heads": 16,
    "num_kv_heads": 16,
    "linear_attention_state_policy": "reset_per_chunk",
    "chunk_tokens": 2048,
    "tail_policy": "commit",
    "output_gate_type": "silu",
    "output_gate_bias": false,
    "output_gate_softcap_enabled": true,
    "output_gate_softcap_limit": 2.0,
    "stable_gdn2_sqrt_erase_gate": true,
    "backbone_gdn_override": false
  },
  "auto_map": {
    "AutoConfig": "configuration_memt.MemTQwen3_5MoeConfig",
    "AutoModelForCausalLM": "modeling_memt.MemTQwen3_5MoeForCausalLM"
  }
}

	{
	"model_type": "memt_qwen3_5_moe",
	"pad_token_id": 248044,
	"architectures": [
	"MemTQwen3_5MoeForCausalLM"
	],
	"torch_dtype": "bfloat16",
	"tie_word_embeddings": false,
	"backbone_configs": {
	"model_type": "qwen3_5_moe",
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"bos_token_id": 248044,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 32,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"model_type": "qwen3_5_moe_text",
	"moe_intermediate_size": 512,
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 16,
	"num_experts": 256,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"output_router_logits": false,
	"pad_token_id": null,
	"partial_rotary_factor": 0.25,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"router_aux_loss_coef": 0.001,
	"shared_expert_intermediate_size": 512,
	"tie_word_embeddings": false,
	"use_cache": true,
	"vocab_size": 248320
	}
	},
	"memt": {
	"memory_update_mode": "token",
	"gdn_version": "stable_gdn2",
	"memory_use_short_conv": false,
	"memory_head_mode": "mha",
	"memory_read_scale": "k_inv_sqrt",
	"num_memory_heads": 16,
	"num_kv_heads": 16,
	"linear_attention_state_policy": "reset_per_chunk",
	"chunk_tokens": 2048,
	"tail_policy": "commit",
	"output_gate_type": "silu",
	"output_gate_bias": false,
	"output_gate_softcap_enabled": true,
	"output_gate_softcap_limit": 2.0,
	"stable_gdn2_sqrt_erase_gate": true,
	"backbone_gdn_override": false
	},
	"auto_map": {
	"AutoConfig": "configuration_memt.MemTQwen3_5MoeConfig",
	"AutoModelForCausalLM": "modeling_memt.MemTQwen3_5MoeForCausalLM"
	}
	}