Instructions to use Grimlabs/GrimBoost-01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Grimlabs/GrimBoost-01 with Transformers:

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

pipe = pipeline("text-generation", model="Grimlabs/GrimBoost-01")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Grimlabs/GrimBoost-01")
model = AutoModelForCausalLM.from_pretrained("Grimlabs/GrimBoost-01", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Grimlabs/GrimBoost-01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Grimlabs/GrimBoost-01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Grimlabs/GrimBoost-01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Grimlabs/GrimBoost-01

SGLang

How to use Grimlabs/GrimBoost-01 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 "Grimlabs/GrimBoost-01" \
    --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": "Grimlabs/GrimBoost-01",
		"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 "Grimlabs/GrimBoost-01" \
        --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": "Grimlabs/GrimBoost-01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Grimlabs/GrimBoost-01 with Docker Model Runner:
```
docker model run hf.co/Grimlabs/GrimBoost-01
```

GrimBoost-01 / validation.json

cheezeborger

Claude Code

Publish GrimBoost-01 model card, FP32 drafter, and runtime

60e7bb5 verified 12 days ago

Raw History Blame Contribute Delete

1.26 kB

{
  "passed": true,
  "device": "cpu",
  "dtype": "float32",
  "trust_remote_code": false,
  "all_native_weights_bit_identical": true,
  "parameters": 19126656,
  "rows": [
    {
      "input_tokens": 24,
      "generated_tokens": 24,
      "max_abs_logit_difference": 0.0,
      "cached_max_abs_logit_difference": 0.0,
      "all_greedy_ids_match": true,
      "tokenizer_roundtrip": true
    },
    {
      "input_tokens": 28,
      "generated_tokens": 24,
      "max_abs_logit_difference": 0.0,
      "cached_max_abs_logit_difference": 0.0,
      "all_greedy_ids_match": true,
      "tokenizer_roundtrip": true
    },
    {
      "input_tokens": 35,
      "generated_tokens": 24,
      "max_abs_logit_difference": 0.0,
      "cached_max_abs_logit_difference": 0.0,
      "all_greedy_ids_match": true,
      "tokenizer_roundtrip": true
    },
    {
      "input_tokens": 200,
      "generated_tokens": 24,
      "max_abs_logit_difference": 0.0,
      "cached_max_abs_logit_difference": 0.0,
      "all_greedy_ids_match": true,
      "tokenizer_roundtrip": true
    }
  ],
  "adaptation_provenance": {
    "target": null,
    "observation_tokens": 0,
    "budget_known": true
  },
  "scope": "drafter format interoperability; not a new target-speed benchmark"
}

	{
	"passed": true,
	"device": "cpu",
	"dtype": "float32",
	"trust_remote_code": false,
	"all_native_weights_bit_identical": true,
	"parameters": 19126656,
	"rows": [
	{
	"input_tokens": 24,
	"generated_tokens": 24,
	"max_abs_logit_difference": 0.0,
	"cached_max_abs_logit_difference": 0.0,
	"all_greedy_ids_match": true,
	"tokenizer_roundtrip": true
	},
	{
	"input_tokens": 28,
	"generated_tokens": 24,
	"max_abs_logit_difference": 0.0,
	"cached_max_abs_logit_difference": 0.0,
	"all_greedy_ids_match": true,
	"tokenizer_roundtrip": true
	},
	{
	"input_tokens": 35,
	"generated_tokens": 24,
	"max_abs_logit_difference": 0.0,
	"cached_max_abs_logit_difference": 0.0,
	"all_greedy_ids_match": true,
	"tokenizer_roundtrip": true
	},
	{
	"input_tokens": 200,
	"generated_tokens": 24,
	"max_abs_logit_difference": 0.0,
	"cached_max_abs_logit_difference": 0.0,
	"all_greedy_ids_match": true,
	"tokenizer_roundtrip": true
	}
	],
	"adaptation_provenance": {
	"target": null,
	"observation_tokens": 0,
	"budget_known": true
	},
	"scope": "drafter format interoperability; not a new target-speed benchmark"
	}