Instructions to use ShacklesLay/CPT4task2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ShacklesLay/CPT4task2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ShacklesLay/CPT4task2")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ShacklesLay/CPT4task2") model = AutoModelForSeq2SeqLM.from_pretrained("ShacklesLay/CPT4task2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ShacklesLay/CPT4task2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ShacklesLay/CPT4task2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ShacklesLay/CPT4task2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ShacklesLay/CPT4task2
- SGLang
How to use ShacklesLay/CPT4task2 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 "ShacklesLay/CPT4task2" \ --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": "ShacklesLay/CPT4task2", "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 "ShacklesLay/CPT4task2" \ --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": "ShacklesLay/CPT4task2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ShacklesLay/CPT4task2 with Docker Model Runner:
docker model run hf.co/ShacklesLay/CPT4task2
File size: 1,797 Bytes
5387e29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 | {
"_name_or_path": "./experiments/fnlp/cpt-large_lr_2.1e-05_bsz_8_sd_44",
"activation_dropout": 0.1,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"CPTForConditionalGeneration"
],
"attention_dropout": 0.1,
"bos_token_id": 101,
"classif_dropout": 0.1,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 4,
"decoder_start_token_id": 102,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 24,
"eos_token_id": 102,
"forced_eos_token_id": 102,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_position_embeddings": 1024,
"model_type": "bart",
"no_repeat_ngram_size": 3,
"normalize_before": false,
"normalize_embedding": true,
"num_beams": 4,
"num_hidden_layers": 24,
"pad_token_id": 0,
"scale_embedding": false,
"task_specific_params": {
"summarization": {
"length_penalty": 1.0,
"max_length": 128,
"min_length": 12,
"num_beams": 4
},
"summarization_cnn": {
"length_penalty": 2.0,
"max_length": 142,
"min_length": 56,
"num_beams": 4
},
"summarization_xsum": {
"length_penalty": 1.0,
"max_length": 62,
"min_length": 11,
"num_beams": 6
}
},
"tokenizer_class": "BertTokenizer",
"torch_dtype": "float32",
"transformers_version": "4.30.0.dev0",
"use_cache": true,
"vocab_size": 51288
}
|