Text Generation
Transformers
Safetensors
English
llama
dental
medical
healthcare
clinical
llama-3.1
cpt
sft
dpo
qlora
unsloth
pall
text-generation-inference
Instructions to use Harisundar/PALL-Text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Harisundar/PALL-Text with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Harisundar/PALL-Text")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Harisundar/PALL-Text") model = AutoModelForCausalLM.from_pretrained("Harisundar/PALL-Text", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Harisundar/PALL-Text with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Harisundar/PALL-Text" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Harisundar/PALL-Text", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Harisundar/PALL-Text
- SGLang
How to use Harisundar/PALL-Text 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 "Harisundar/PALL-Text" \ --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": "Harisundar/PALL-Text", "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 "Harisundar/PALL-Text" \ --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": "Harisundar/PALL-Text", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use Harisundar/PALL-Text with Docker Model Runner:
docker model run hf.co/Harisundar/PALL-Text
Remove college name from model card
Browse files
README.md
CHANGED
|
@@ -29,7 +29,7 @@ under 4-bit QLoRA on a **single A100-40GB GPU** for roughly **\$20** of cloud co
|
|
| 29 |
This repository hosts the **final, fully-merged bf16 model** (all three adapters merged into
|
| 30 |
the base weights — no PEFT adapter required at inference).
|
| 31 |
|
| 32 |
-
- **Developed by:** Harisundar R
|
| 33 |
- **Base model:** [`unsloth/Meta-Llama-3.1-8B`](https://huggingface.co/unsloth/Meta-Llama-3.1-8B)
|
| 34 |
- **Code:** [PALL on GitHub](https://github.com/HARISUNDARRAJENDRAN/PALL)
|
| 35 |
- **Companion VLM:** [`Harisundar/PALL-VLM`](https://huggingface.co/Harisundar/PALL-VLM)
|
|
@@ -204,7 +204,7 @@ If you use PALL, please cite:
|
|
| 204 |
author = {Rajendran, Harisundar},
|
| 205 |
year = {2026},
|
| 206 |
howpublished = {\url{https://huggingface.co/Harisundar/PALL-Text}},
|
| 207 |
-
|
| 208 |
}
|
| 209 |
```
|
| 210 |
|
|
|
|
| 29 |
This repository hosts the **final, fully-merged bf16 model** (all three adapters merged into
|
| 30 |
the base weights — no PEFT adapter required at inference).
|
| 31 |
|
| 32 |
+
- **Developed by:** Harisundar R
|
| 33 |
- **Base model:** [`unsloth/Meta-Llama-3.1-8B`](https://huggingface.co/unsloth/Meta-Llama-3.1-8B)
|
| 34 |
- **Code:** [PALL on GitHub](https://github.com/HARISUNDARRAJENDRAN/PALL)
|
| 35 |
- **Companion VLM:** [`Harisundar/PALL-VLM`](https://huggingface.co/Harisundar/PALL-VLM)
|
|
|
|
| 204 |
author = {Rajendran, Harisundar},
|
| 205 |
year = {2026},
|
| 206 |
howpublished = {\url{https://huggingface.co/Harisundar/PALL-Text}},
|
| 207 |
+
|
| 208 |
}
|
| 209 |
```
|
| 210 |
|