Instructions to use HFShishir/BanglaFast-500M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HFShishir/BanglaFast-500M-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HFShishir/BanglaFast-500M-Instruct")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HFShishir/BanglaFast-500M-Instruct") model = AutoModelForCausalLM.from_pretrained("HFShishir/BanglaFast-500M-Instruct", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HFShishir/BanglaFast-500M-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HFShishir/BanglaFast-500M-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HFShishir/BanglaFast-500M-Instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/HFShishir/BanglaFast-500M-Instruct
- SGLang
How to use HFShishir/BanglaFast-500M-Instruct 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 "HFShishir/BanglaFast-500M-Instruct" \ --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": "HFShishir/BanglaFast-500M-Instruct", "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 "HFShishir/BanglaFast-500M-Instruct" \ --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": "HFShishir/BanglaFast-500M-Instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use HFShishir/BanglaFast-500M-Instruct with Docker Model Runner:
docker model run hf.co/HFShishir/BanglaFast-500M-Instruct
|
Download README.md from HFShishir/BanglaFast-500M-Instruct: direct link, hf CLI and curl.
- Browser
- Download file 1.71 kB
-
https://huggingface.co/HFShishir/BanglaFast-500M-Instruct/resolve/main/README.md
- Command line
-
hf download hf://HFShishir/BanglaFast-500M-Instruct/README.md
-
curl -L -o README.md https://huggingface.co/HFShishir/BanglaFast-500M-Instruct/resolve/main/README.md
1.71 kB
| library_name: transformers | |
| license: apache-2.0 | |
| base_model: HFShishir/BanglaFast-500M-Foundation-SLM | |
| tags: | |
| - generated_from_trainer | |
| model-index: | |
| - name: BanglaFast-500M-Instruct | |
| 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. --> | |
| # BanglaFast-500M-Instruct | |
| This model is a fine-tuned version of [HFShishir/BanglaFast-500M-Foundation-SLM](https://huggingface.co/HFShishir/BanglaFast-500M-Foundation-SLM) on an unknown dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.0433 | |
| ## 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: 8 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - gradient_accumulation_steps: 4 | |
| - total_train_batch_size: 32 | |
| - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments | |
| - lr_scheduler_type: cosine | |
| - lr_scheduler_warmup_steps: 50 | |
| - num_epochs: 3 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | | |
| |:-------------:|:-----:|:----:|:---------------:| | |
| | 0.0512 | 1.0 | 179 | 0.0491 | | |
| | 0.0440 | 2.0 | 358 | 0.0437 | | |
| | 0.0427 | 3.0 | 537 | 0.0433 | | |
| ### Framework versions | |
| - Transformers 5.22.1 | |
| - Pytorch 2.14.1+cu130 | |
| - Datasets 4.8.5 | |
| - Tokenizers 0.23.3 | |