Instructions to use nferruz/1.24.3.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nferruz/1.24.3.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="nferruz/1.24.3.1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("nferruz/1.24.3.1") model = AutoModelForCausalLM.from_pretrained("nferruz/1.24.3.1") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use nferruz/1.24.3.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "nferruz/1.24.3.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nferruz/1.24.3.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/nferruz/1.24.3.1
- SGLang
How to use nferruz/1.24.3.1 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 "nferruz/1.24.3.1" \ --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": "nferruz/1.24.3.1", "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 "nferruz/1.24.3.1" \ --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": "nferruz/1.24.3.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use nferruz/1.24.3.1 with Docker Model Runner:
docker model run hf.co/nferruz/1.24.3.1
output
This model is a fine-tuned version of /home/woody/b114cb/b114cb10/zymCTRL/train/output/ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1872
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: 8e-05
- train_batch_size: 1
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9089 | 0.09 | 10 | 0.9186 |
| 0.6625 | 0.18 | 20 | 0.5026 |
| 0.6228 | 0.27 | 30 | 0.4214 |
| 0.6733 | 0.35 | 40 | 0.3994 |
| 0.5581 | 0.44 | 50 | 0.3381 |
| 0.3853 | 0.53 | 60 | 0.3290 |
| 0.4146 | 0.62 | 70 | 0.2982 |
| 0.4702 | 0.71 | 80 | 0.2852 |
| 0.2309 | 0.8 | 90 | 0.3018 |
| 0.4707 | 0.88 | 100 | 0.2675 |
| 0.3001 | 0.97 | 110 | 0.2527 |
| 0.4044 | 1.06 | 120 | 0.2536 |
| 0.3605 | 1.15 | 130 | 0.2479 |
| 0.2309 | 1.24 | 140 | 0.2304 |
| 0.2481 | 1.33 | 150 | 0.2185 |
| 0.3251 | 1.42 | 160 | 0.2110 |
| 0.227 | 1.5 | 170 | 0.2128 |
| 0.238 | 1.59 | 180 | 0.2065 |
| 0.2171 | 1.68 | 190 | 0.2167 |
| 0.2844 | 1.77 | 200 | 0.2067 |
| 0.2822 | 1.86 | 210 | 0.2065 |
| 0.2111 | 1.95 | 220 | 0.2021 |
| 0.1915 | 2.04 | 230 | 0.2136 |
| 0.122 | 2.12 | 240 | 0.2245 |
| 0.1845 | 2.21 | 250 | 0.2035 |
| 0.1597 | 2.3 | 260 | 0.1980 |
| 0.1037 | 2.39 | 270 | 0.1939 |
| 0.109 | 2.48 | 280 | 0.1946 |
| 0.1312 | 2.57 | 290 | 0.1936 |
| 0.2261 | 2.65 | 300 | 0.1918 |
| 0.113 | 2.74 | 310 | 0.1863 |
| 0.1762 | 2.83 | 320 | 0.1790 |
| 0.1431 | 2.92 | 330 | 0.1783 |
| 0.2109 | 3.01 | 340 | 0.1761 |
| 0.0885 | 3.1 | 350 | 0.1844 |
| 0.0647 | 3.19 | 360 | 0.1922 |
| 0.126 | 3.27 | 370 | 0.1909 |
| 0.0965 | 3.36 | 380 | 0.1878 |
| 0.1068 | 3.45 | 390 | 0.1915 |
| 0.0973 | 3.54 | 400 | 0.1814 |
| 0.074 | 3.63 | 410 | 0.1835 |
| 0.0899 | 3.72 | 420 | 0.1821 |
| 0.1126 | 3.81 | 430 | 0.1807 |
| 0.0969 | 3.89 | 440 | 0.1776 |
| 0.0644 | 3.98 | 450 | 0.1764 |
| 0.049 | 4.07 | 460 | 0.1785 |
| 0.0466 | 4.16 | 470 | 0.1822 |
| 0.0545 | 4.25 | 480 | 0.1870 |
| 0.0391 | 4.34 | 490 | 0.1908 |
| 0.0614 | 4.42 | 500 | 0.1918 |
| 0.0597 | 4.51 | 510 | 0.1895 |
| 0.0461 | 4.6 | 520 | 0.1863 |
| 0.0456 | 4.69 | 530 | 0.1867 |
| 0.0438 | 4.78 | 540 | 0.1867 |
| 0.0394 | 4.87 | 550 | 0.1871 |
| 0.0454 | 4.96 | 560 | 0.1872 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.12.1+cu116
- Datasets 2.10.0
- Tokenizers 0.12.1
- Downloads last month
- 3