Instructions to use AIMadeSimpleResearch/AIMS-1-128M-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIMadeSimpleResearch/AIMS-1-128M-base with Transformers:

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

pipe = pipeline("text-generation", model="AIMadeSimpleResearch/AIMS-1-128M-base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AIMadeSimpleResearch/AIMS-1-128M-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AIMadeSimpleResearch/AIMS-1-128M-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIMadeSimpleResearch/AIMS-1-128M-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIMadeSimpleResearch/AIMS-1-128M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AIMadeSimpleResearch/AIMS-1-128M-base

SGLang

How to use AIMadeSimpleResearch/AIMS-1-128M-base 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 "AIMadeSimpleResearch/AIMS-1-128M-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIMadeSimpleResearch/AIMS-1-128M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "AIMadeSimpleResearch/AIMS-1-128M-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIMadeSimpleResearch/AIMS-1-128M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AIMadeSimpleResearch/AIMS-1-128M-base with Docker Model Runner:
```
docker model run hf.co/AIMadeSimpleResearch/AIMS-1-128M-base
```

AIMS-1-128M-base / verification.json

Samwise63

Upload verified custom BabyAIMS causal language model

afbd8e2 verified about 1 month ago

Raw History Blame Contribute Delete

2.19 kB

{
  "status": "passed",
  "checkpoint_sha256": "20803108eaf90725efa5fca1c0681a0b00bef3910d7cc1c82f5f65a012f8036d",
  "reference_notebook_sha256": "cbe479ab579025a5faa0b220373dec4e15485099d6556b13145e451230bd1833",
  "export_dtype": "float32",
  "parity_tolerances": {
    "rtol": 0,
    "atol": 0
  },
  "original_model_parity": [
    {
      "length": 1,
      "max_absolute_logit_error": 0.0
    },
    {
      "length": 7,
      "max_absolute_logit_error": 0.0
    },
    {
      "length": 31,
      "max_absolute_logit_error": 0.0
    },
    {
      "length": 1024,
      "max_absolute_logit_error": 0.0
    }
  ],
  "tokenizer": {
    "examples_checked": 13,
    "vocab_size": 50260
  },
  "reload_checks": {
    "tokenizer": {
      "examples_checked": 13,
      "vocab_size": 50260
    },
    "reload": "passed",
    "rope_buffers": "passed",
    "padded_logits": "passed",
    "generation": "passed",
    "causal_loss": 7.8538432121276855,
    "reload_parity_tolerances": {
      "rtol": 1e-06,
      "atol": 1e-06
    },
    "sample_text": [
      "Hello.\n-",
      "Every effort moves you.\nI"
    ]
  },
  "versions": {
    "torch": "2.11.0+cpu",
    "transformers": "5.17.0",
    "tokenizers": "0.23.2",
    "tiktoken": "0.14.0",
    "safetensors": "0.8.0",
    "huggingface_hub": "1.31.0"
  },
  "file_sha256": {
    "modeling_baby_aims.py": "e1acbbe55cf64cf21da8c8b8a4a40a07b0966e5ce938b55f0160e4855e13373a",
    "configuration_baby_aims.py": "6e0c93effa91d65c0a18655a33c3a5abe5cf00ac8c5c67fe10dcc70c9b0ee759",
    "notebook_components.py": "b4e55a5d6d02c542dfd5a0eea356fac9b1455df86f384b15da6a435cb8534fc3",
    "config.json": "20eebefea4b254d190b2228b1d1f2c08561b98390ada239676136842f974a355",
    "generation_config.json": "6658ca7cb4c613583d0dc9455db3ae45818397fc3d463874b11d8a4d02a458b0",
    "model.safetensors": "28ef40a7f7c069a8a664ae7ac88676bdb808fd69d9a94026e16f84277ceba316",
    "tokenizer.json": "d4c5f9479fd933e3dc2549b823181ac501db9f17b856850b18085f39191410a5",
    "tokenizer_config.json": "55374a810790a1b70c687b08aebcbec3733f6f585fa759b406141800831db7f0",
    "requirements.txt": "317bdc607d55e5486431e9aecc81b38d0e4333fb6e236a3fbf38bb81c043965d"
  }
}

	{
	"status": "passed",
	"checkpoint_sha256": "20803108eaf90725efa5fca1c0681a0b00bef3910d7cc1c82f5f65a012f8036d",
	"reference_notebook_sha256": "cbe479ab579025a5faa0b220373dec4e15485099d6556b13145e451230bd1833",
	"export_dtype": "float32",
	"parity_tolerances": {
	"rtol": 0,
	"atol": 0
	},
	"original_model_parity": [
	{
	"length": 1,
	"max_absolute_logit_error": 0.0
	},
	{
	"length": 7,
	"max_absolute_logit_error": 0.0
	},
	{
	"length": 31,
	"max_absolute_logit_error": 0.0
	},
	{
	"length": 1024,
	"max_absolute_logit_error": 0.0
	}
	],
	"tokenizer": {
	"examples_checked": 13,
	"vocab_size": 50260
	},
	"reload_checks": {
	"tokenizer": {
	"examples_checked": 13,
	"vocab_size": 50260
	},
	"reload": "passed",
	"rope_buffers": "passed",
	"padded_logits": "passed",
	"generation": "passed",
	"causal_loss": 7.8538432121276855,
	"reload_parity_tolerances": {
	"rtol": 1e-06,
	"atol": 1e-06
	},
	"sample_text": [
	"Hello.\n-",
	"Every effort moves you.\nI"
	]
	},
	"versions": {
	"torch": "2.11.0+cpu",
	"transformers": "5.17.0",
	"tokenizers": "0.23.2",
	"tiktoken": "0.14.0",
	"safetensors": "0.8.0",
	"huggingface_hub": "1.31.0"
	},
	"file_sha256": {
	"modeling_baby_aims.py": "e1acbbe55cf64cf21da8c8b8a4a40a07b0966e5ce938b55f0160e4855e13373a",
	"configuration_baby_aims.py": "6e0c93effa91d65c0a18655a33c3a5abe5cf00ac8c5c67fe10dcc70c9b0ee759",
	"notebook_components.py": "b4e55a5d6d02c542dfd5a0eea356fac9b1455df86f384b15da6a435cb8534fc3",
	"config.json": "20eebefea4b254d190b2228b1d1f2c08561b98390ada239676136842f974a355",
	"generation_config.json": "6658ca7cb4c613583d0dc9455db3ae45818397fc3d463874b11d8a4d02a458b0",
	"model.safetensors": "28ef40a7f7c069a8a664ae7ac88676bdb808fd69d9a94026e16f84277ceba316",
	"tokenizer.json": "d4c5f9479fd933e3dc2549b823181ac501db9f17b856850b18085f39191410a5",
	"tokenizer_config.json": "55374a810790a1b70c687b08aebcbec3733f6f585fa759b406141800831db7f0",
	"requirements.txt": "317bdc607d55e5486431e9aecc81b38d0e4333fb6e236a3fbf38bb81c043965d"
	}
	}