Instructions to use scribekey/scribekey-cleanup-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use scribekey/scribekey-cleanup-fast with Transformers:

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

pipe = pipeline("text-generation", model="scribekey/scribekey-cleanup-fast")
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("scribekey/scribekey-cleanup-fast")
model = AutoModelForCausalLM.from_pretrained("scribekey/scribekey-cleanup-fast", 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 scribekey/scribekey-cleanup-fast with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/scribekey/scribekey-cleanup-fast

SGLang

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

Docker Model Runner
How to use scribekey/scribekey-cleanup-fast with Docker Model Runner:
```
docker model run hf.co/scribekey/scribekey-cleanup-fast
```

scribekey-cleanup-fast / evaluation.json

kind-hill

ScribeKey Fast v1.1: new weights and cards

c484dad verified 12 days ago

Raw History Blame Contribute Delete

1.48 kB

{
  "artifact_sha256": "2dfd7463ae0a8ca7dd2e4abebeed9cc77a584569b9c99dc9e68ad85f1399b55a",
  "quantization": "Q8_0",
  "scope": "ScribeKey app-boundary, paired against ScribeKey Fast v1 with identical controls",
  "controls": {
    "styling": "semi-casual",
    "structure": "prose",
    "context": "general"
  },
  "benchmark": {
    "name": "ScribeKey holdout-v1",
    "scored_rows": 7516,
    "total_rows": 7524,
    "groups_resampled": true,
    "hidden_rows_distributed": false
  },
  "metrics_vs_v1": {
    "self_correction_ter": [
      -0.036,
      -0.046,
      -0.026
    ],
    "self_correction_ter_questions": [
      -0.048,
      -0.065,
      -0.03
    ],
    "self_correction_ter_written": [
      -0.023,
      -0.032,
      -0.014
    ],
    "exact_pp": [
      3.3,
      2.4,
      4.3
    ],
    "clean_input_damage_pp": [
      -0.9,
      -2.1,
      0.0
    ],
    "new_values_pp": [
      -0.3,
      -0.7,
      0.1
    ]
  },
  "metric_format": "[difference, 95% lower, 95% upper], v1.1 minus v1",
  "gates": "pre-registered: correction TER upper < 0, exact lower > -1 pt, new values upper <= +0.5 pt; all pass",
  "bf16_quality_benchmark": "not measured",
  "final_artifact_phone": "not measured",
  "midrange_phone": "not measured",
  "limitations": [
    "model can change or omit meaning",
    "list recall low",
    "source/data provenance inherited in part",
    "phone latency assumed from v1's identical architecture and size, not measured"
  ]
}

	{
	"artifact_sha256": "2dfd7463ae0a8ca7dd2e4abebeed9cc77a584569b9c99dc9e68ad85f1399b55a",
	"quantization": "Q8_0",
	"scope": "ScribeKey app-boundary, paired against ScribeKey Fast v1 with identical controls",
	"controls": {
	"styling": "semi-casual",
	"structure": "prose",
	"context": "general"
	},
	"benchmark": {
	"name": "ScribeKey holdout-v1",
	"scored_rows": 7516,
	"total_rows": 7524,
	"groups_resampled": true,
	"hidden_rows_distributed": false
	},
	"metrics_vs_v1": {
	"self_correction_ter": [
	-0.036,
	-0.046,
	-0.026
	],
	"self_correction_ter_questions": [
	-0.048,
	-0.065,
	-0.03
	],
	"self_correction_ter_written": [
	-0.023,
	-0.032,
	-0.014
	],
	"exact_pp": [
	3.3,
	2.4,
	4.3
	],
	"clean_input_damage_pp": [
	-0.9,
	-2.1,
	0.0
	],
	"new_values_pp": [
	-0.3,
	-0.7,
	0.1
	]
	},
	"metric_format": "[difference, 95% lower, 95% upper], v1.1 minus v1",
	"gates": "pre-registered: correction TER upper < 0, exact lower > -1 pt, new values upper <= +0.5 pt; all pass",
	"bf16_quality_benchmark": "not measured",
	"final_artifact_phone": "not measured",
	"midrange_phone": "not measured",
	"limitations": [
	"model can change or omit meaning",
	"list recall low",
	"source/data provenance inherited in part",
	"phone latency assumed from v1's identical architecture and size, not measured"
	]
	}