Instructions to use gnumanth/scribelm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gnumanth/scribelm with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("gnumanth/scribelm", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gnumanth/scribelm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/gnumanth/scribelm

SGLang

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

Docker Model Runner
How to use gnumanth/scribelm with Docker Model Runner:
```
docker model run hf.co/gnumanth/scribelm
```

scribelm / config.json

gnumanth

Publish GCP-trained intact 30-layer 134.8M ScribeLMForAuthoring FP32 + Int8 ONNX

3bf7870 verified 14 days ago

Raw History Blame Contribute Delete

697 Bytes

{
  "architectures": [
    "ScribeLMForAuthoring"
  ],
  "auto_map": {
    "AutoConfig": "modeling_scribelm.ScribeLMConfig",
    "AutoModel": "modeling_scribelm.ScribeLMForAuthoring"
  },
  "base_model_name": "HuggingFaceTB/SmolLM2-135M-Instruct",
  "dropout": 0.1,
  "freeze_bottom_layers": 20,
  "hidden_act": "silu",
  "hidden_size": 576,
  "intermediate_size": 1536,
  "max_position_embeddings": 2048,
  "model_type": "scribelm",
  "num_attention_heads": 9,
  "num_hidden_layers": 30,
  "num_key_value_heads": 3,
  "num_style_axes": 5,
  "num_tasks": 4,
  "rms_norm_eps": 1e-05,
  "rope_theta": 100000.0,
  "torch_dtype": "float32",
  "transformers_version": "4.48.3",
  "vocab_size": 49152
}

	{
	"architectures": [
	"ScribeLMForAuthoring"
	],
	"auto_map": {
	"AutoConfig": "modeling_scribelm.ScribeLMConfig",
	"AutoModel": "modeling_scribelm.ScribeLMForAuthoring"
	},
	"base_model_name": "HuggingFaceTB/SmolLM2-135M-Instruct",
	"dropout": 0.1,
	"freeze_bottom_layers": 20,
	"hidden_act": "silu",
	"hidden_size": 576,
	"intermediate_size": 1536,
	"max_position_embeddings": 2048,
	"model_type": "scribelm",
	"num_attention_heads": 9,
	"num_hidden_layers": 30,
	"num_key_value_heads": 3,
	"num_style_axes": 5,
	"num_tasks": 4,
	"rms_norm_eps": 1e-05,
	"rope_theta": 100000.0,
	"torch_dtype": "float32",
	"transformers_version": "4.48.3",
	"vocab_size": 49152
	}