Instructions to use eleanorbeers/glue_clm-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eleanorbeers/glue_clm-model with Transformers:

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

pipe = pipeline("text-generation", model="eleanorbeers/glue_clm-model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eleanorbeers/glue_clm-model")
model = AutoModelForCausalLM.from_pretrained("eleanorbeers/glue_clm-model")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eleanorbeers/glue_clm-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/eleanorbeers/glue_clm-model

SGLang

How to use eleanorbeers/glue_clm-model 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 "eleanorbeers/glue_clm-model" \
    --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": "eleanorbeers/glue_clm-model",
		"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 "eleanorbeers/glue_clm-model" \
        --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": "eleanorbeers/glue_clm-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eleanorbeers/glue_clm-model with Docker Model Runner:
```
docker model run hf.co/eleanorbeers/glue_clm-model
```

glue_clm-model

File size: 1,554 Bytes

801e006

{
  "_name_or_path": "microsoft/prophetnet-large-uncased",
  "activation_dropout": 0.1,
  "activation_function": "gelu",
  "add_cross_attention": true,
  "architectures": [
    "ProphetNetForCausalLM"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 102,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_max_position_embeddings": 514,
  "decoder_start_token_id": 102,
  "disable_ngram_loss": false,
  "dropout": 0.1,
  "early_stopping": null,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_max_position_embeddings": 513,
  "eos_token_id": 102,
  "eps": 0.0,
  "hidden_size": 1024,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "is_decoder": true,
  "is_encoder_decoder": false,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "length_penalty": null,
  "max_length": null,
  "max_position_embeddings": 512,
  "model_type": "prophetnet",
  "ngram": 2,
  "no_repeat_ngram_size": null,
  "num_beams": null,
  "num_buckets": 32,
  "num_decoder_attention_heads": 16,
  "num_decoder_layers": 12,
  "num_encoder_attention_heads": 16,
  "num_encoder_layers": 12,
  "output_past": false,
  "pad_token_id": 0,
  "prefix": " ",
  "relative_max_distance": 128,
  "task_specific_params": {
    "summarization": {
      "early_stopping": true,
      "length_penalty": 2.0,
      "no_repeat_ngram_size": 3,
      "num_beams": 4
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.46.2",
  "use_cache": true,
  "vocab_size": 30522
}