Instructions to use RetentionLabs/TTTPilot-Q-5B-Thinking-MAC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RetentionLabs/TTTPilot-Q-5B-Thinking-MAC with Transformers:

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

pipe = pipeline("text-generation", model="RetentionLabs/TTTPilot-Q-5B-Thinking-MAC", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("RetentionLabs/TTTPilot-Q-5B-Thinking-MAC", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RetentionLabs/TTTPilot-Q-5B-Thinking-MAC with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RetentionLabs/TTTPilot-Q-5B-Thinking-MAC"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RetentionLabs/TTTPilot-Q-5B-Thinking-MAC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RetentionLabs/TTTPilot-Q-5B-Thinking-MAC

SGLang

How to use RetentionLabs/TTTPilot-Q-5B-Thinking-MAC 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 "RetentionLabs/TTTPilot-Q-5B-Thinking-MAC" \
    --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": "RetentionLabs/TTTPilot-Q-5B-Thinking-MAC",
		"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 "RetentionLabs/TTTPilot-Q-5B-Thinking-MAC" \
        --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": "RetentionLabs/TTTPilot-Q-5B-Thinking-MAC",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RetentionLabs/TTTPilot-Q-5B-Thinking-MAC with Docker Model Runner:
```
docker model run hf.co/RetentionLabs/TTTPilot-Q-5B-Thinking-MAC
```

TTTPilot-Q-5B-Thinking-MAC / config.json

RetentionLabs

Upload folder using huggingface_hub

2510087 verified 6 months ago

Raw

History Blame Contribute Delete

1.24 kB

	{
	"model_type": "tttpilot_mac",
	"architectures": [
	"TTTPilotMACForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "modeling_tttpilot_mac.TTTPilotMACConfig",
	"AutoModel": "modeling_tttpilot_mac.TTTPilotMACModel",
	"AutoModelForCausalLM": "modeling_tttpilot_mac.TTTPilotMACForCausalLM"
	},
	"vocab_size": 151936,
	"bos_token_id": 151643,
	"eos_token_id": 151645,
	"pad_token_id": 151643,
	"tie_word_embeddings": true,
	"hidden_size": 2048,
	"hidden_act": "silu",
	"initializer_range": 0.02,
	"rms_norm_eps": 1e-06,
	"max_position_embeddings": 262144,
	"num_memory_layers": 24,
	"memory_intermediate_size": 5504,
	"num_attention_heads": 32,
	"mini_batch_size": 16,
	"ttt_base_lr": 1.0,
	"ttt_layer_type": "linear",
	"pre_conv": true,
	"conv_kernel": 4,
	"use_gate": true,
	"share_qk": true,
	"fixed_memory_size": 64,
	"num_core_layers": 36,
	"core_intermediate_size": 9728,
	"num_key_value_heads": 8,
	"head_dim": 128,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"rope_theta": 5000000,
	"rope_scaling": null,
	"sliding_window": null,
	"use_cache": true,
	"scan_checkpoint_group_size": 0,
	"torch_dtype": "bfloat16",
	"pretraining_tp": 1
	}