Instructions to use CLMBR/superlative-quantifier-transformer-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CLMBR/superlative-quantifier-transformer-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CLMBR/superlative-quantifier-transformer-1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CLMBR/superlative-quantifier-transformer-1") model = AutoModelForCausalLM.from_pretrained("CLMBR/superlative-quantifier-transformer-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CLMBR/superlative-quantifier-transformer-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CLMBR/superlative-quantifier-transformer-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CLMBR/superlative-quantifier-transformer-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CLMBR/superlative-quantifier-transformer-1
- SGLang
How to use CLMBR/superlative-quantifier-transformer-1 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 "CLMBR/superlative-quantifier-transformer-1" \ --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": "CLMBR/superlative-quantifier-transformer-1", "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 "CLMBR/superlative-quantifier-transformer-1" \ --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": "CLMBR/superlative-quantifier-transformer-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CLMBR/superlative-quantifier-transformer-1 with Docker Model Runner:
docker model run hf.co/CLMBR/superlative-quantifier-transformer-1
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: superlative-quantifier-transformer-1 | |
| results: [] | |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You | |
| should probably proofread and complete it, then remove this comment. --> | |
| # superlative-quantifier-transformer-1 | |
| This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 3.8811 | |
| ## Model description | |
| More information needed | |
| ## Intended uses & limitations | |
| More information needed | |
| ## Training and evaluation data | |
| More information needed | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 5e-05 | |
| - train_batch_size: 32 | |
| - eval_batch_size: 32 | |
| - seed: 1 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - training_steps: 3052726 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:-------:|:---------------:| | |
| | 4.2257 | 0.03 | 76320 | 4.2120 | | |
| | 4.0221 | 1.03 | 152640 | 4.0416 | | |
| | 3.9131 | 0.03 | 228960 | 3.9674 | | |
| | 3.8475 | 1.03 | 305280 | 3.9266 | | |
| | 3.7974 | 0.03 | 381600 | 3.9019 | | |
| | 3.7557 | 1.03 | 457920 | 3.8863 | | |
| | 3.7223 | 0.03 | 534240 | 3.8759 | | |
| | 3.696 | 1.03 | 610560 | 3.8692 | | |
| | 3.668 | 0.03 | 686880 | 3.8648 | | |
| | 3.6404 | 1.03 | 763200 | 3.8614 | | |
| | 3.619 | 0.03 | 839520 | 3.8603 | | |
| | 3.5962 | 1.03 | 915840 | 3.8590 | | |
| | 3.5817 | 0.03 | 992160 | 3.8601 | | |
| | 3.5625 | 0.03 | 1068480 | 3.8599 | | |
| | 3.544 | 0.03 | 1144800 | 3.8615 | | |
| | 3.5279 | 1.03 | 1221120 | 3.8617 | | |
| | 3.5119 | 0.03 | 1297440 | 3.8635 | | |
| | 3.4993 | 1.03 | 1373760 | 3.8644 | | |
| | 3.4836 | 0.03 | 1450080 | 3.8650 | | |
| | 3.4751 | 0.03 | 1526400 | 3.8681 | | |
| | 3.467 | 0.03 | 1602720 | 3.8682 | | |
| | 3.4583 | 0.03 | 1679040 | 3.8708 | | |
| | 3.451 | 1.03 | 1755360 | 3.8718 | | |
| | 3.4441 | 0.03 | 1831680 | 3.8737 | | |
| | 3.429 | 0.03 | 1908000 | 3.8752 | | |
| | 3.4162 | 1.03 | 1984320 | 3.8754 | | |
| | 3.4051 | 0.03 | 2060640 | 3.8770 | | |
| | 3.3914 | 0.03 | 2136960 | 3.8770 | | |
| | 3.3854 | 0.03 | 2213280 | 3.8788 | | |
| | 3.3745 | 1.03 | 2289600 | 3.8804 | | |
| | 3.3613 | 0.03 | 2365920 | 3.8813 | | |
| | 3.3479 | 1.03 | 2442240 | 3.8816 | | |
| | 3.3373 | 0.03 | 2518560 | 3.8827 | | |
| | 3.3284 | 0.03 | 2594880 | 3.8824 | | |
| | 3.3156 | 0.03 | 2671200 | 3.8829 | | |
| | 3.3124 | 1.03 | 2747520 | 3.8831 | | |
| | 3.3082 | 0.03 | 2823840 | 3.8832 | | |
| | 3.3015 | 0.03 | 2900160 | 3.8824 | | |
| | 3.2982 | 1.03 | 2976480 | 3.8816 | | |
| | 3.2944 | 0.02 | 3052726 | 3.8811 | | |
| ### Framework versions | |
| - Transformers 4.33.3 | |
| - Pytorch 2.0.1 | |
| - Datasets 2.12.0 | |
| - Tokenizers 0.13.3 | |