Instructions to use CLMBR/full-transformer-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CLMBR/full-transformer-0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CLMBR/full-transformer-0")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CLMBR/full-transformer-0") model = AutoModelForCausalLM.from_pretrained("CLMBR/full-transformer-0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CLMBR/full-transformer-0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CLMBR/full-transformer-0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CLMBR/full-transformer-0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CLMBR/full-transformer-0
- SGLang
How to use CLMBR/full-transformer-0 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/full-transformer-0" \ --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/full-transformer-0", "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/full-transformer-0" \ --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/full-transformer-0", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CLMBR/full-transformer-0 with Docker Model Runner:
docker model run hf.co/CLMBR/full-transformer-0
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: full2-transformer-0 | |
| 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. --> | |
| # full2-transformer-0 | |
| 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: 3.8599 | |
| ## 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: 0 | |
| - 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 | | |
| |:-------------:|:-----:|:-------:|:---------------:| | |
| | 4.2278 | 0.03 | 76320 | 4.1982 | | |
| | 4.022 | 1.03 | 152640 | 4.0277 | | |
| | 3.9114 | 0.03 | 228960 | 3.9531 | | |
| | 3.8457 | 1.03 | 305280 | 3.9114 | | |
| | 3.7937 | 0.03 | 381600 | 3.8858 | | |
| | 3.754 | 0.03 | 457920 | 3.8699 | | |
| | 3.7241 | 1.03 | 534240 | 3.8603 | | |
| | 3.6953 | 0.03 | 610560 | 3.8520 | | |
| | 3.6648 | 1.03 | 686880 | 3.8463 | | |
| | 3.6391 | 0.03 | 763200 | 3.8440 | | |
| | 3.6181 | 1.03 | 839520 | 3.8425 | | |
| | 3.5968 | 0.03 | 915840 | 3.8439 | | |
| | 3.5813 | 1.03 | 992160 | 3.8418 | | |
| | 3.5607 | 0.03 | 1068480 | 3.8427 | | |
| | 3.5409 | 1.03 | 1144800 | 3.8433 | | |
| | 3.5305 | 0.03 | 1221120 | 3.8444 | | |
| | 3.5122 | 1.03 | 1297440 | 3.8448 | | |
| | 3.4994 | 0.03 | 1373760 | 3.8457 | | |
| | 3.4845 | 1.03 | 1450080 | 3.8475 | | |
| | 3.4776 | 0.03 | 1526400 | 3.8493 | | |
| | 3.4657 | 1.03 | 1602720 | 3.8507 | | |
| | 3.4584 | 0.03 | 1679040 | 3.8513 | | |
| | 3.4537 | 1.03 | 1755360 | 3.8522 | | |
| | 3.4416 | 0.03 | 1831680 | 3.8545 | | |
| | 3.4273 | 0.03 | 1908000 | 3.8565 | | |
| | 3.4147 | 1.03 | 1984320 | 3.8564 | | |
| | 3.4051 | 0.03 | 2060640 | 3.8578 | | |
| | 3.3912 | 1.03 | 2136960 | 3.8585 | | |
| | 3.3848 | 0.03 | 2213280 | 3.8590 | | |
| | 3.3723 | 1.03 | 2289600 | 3.8598 | | |
| | 3.3586 | 0.03 | 2365920 | 3.8602 | | |
| | 3.3545 | 1.03 | 2442240 | 3.8610 | | |
| | 3.3408 | 0.03 | 2518560 | 3.8615 | | |
| | 3.3335 | 1.03 | 2594880 | 3.8624 | | |
| | 3.3191 | 0.03 | 2671200 | 3.8620 | | |
| | 3.3152 | 1.03 | 2747520 | 3.8622 | | |
| | 3.3084 | 0.03 | 2823840 | 3.8619 | | |
| | 3.3053 | 1.03 | 2900160 | 3.8617 | | |
| | 3.3031 | 0.03 | 2976480 | 3.8612 | | |
| | 3.2954 | 1.02 | 3052726 | 3.8599 | | |
| ### Framework versions | |
| - Transformers 4.33.3 | |
| - Pytorch 2.0.1 | |
| - Datasets 2.12.0 | |
| - Tokenizers 0.13.3 | |