Text Generation
Transformers
PyTorch
English
bart
text2text-generation
rag
question answering
retrieval augmented generation
Instructions to use ansukla/task-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ansukla/task-llm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ansukla/task-llm")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ansukla/task-llm") model = AutoModelForSeq2SeqLM.from_pretrained("ansukla/task-llm") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ansukla/task-llm with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ansukla/task-llm" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ansukla/task-llm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ansukla/task-llm
- SGLang
How to use ansukla/task-llm 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 "ansukla/task-llm" \ --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": "ansukla/task-llm", "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 "ansukla/task-llm" \ --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": "ansukla/task-llm", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ansukla/task-llm with Docker Model Runner:
docker model run hf.co/ansukla/task-llm
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,10 +3,25 @@ license: apache-2.0
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: question-answering
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
# Model Card for task-llm
|
| 8 |
|
| 9 |
This model supports abstractive QA tasks. Given a set of passages and a question, it tries to generate a comprehensive answer by reading the passages.
|
|
|
|
| 10 |
|
| 11 |
## Model Details
|
| 12 |
|
|
@@ -53,7 +68,7 @@ qa_sum_client_bart = ClassificationClient(
|
|
| 53 |
url=v100Url,
|
| 54 |
retry=1,
|
| 55 |
)
|
| 56 |
-
# nlm-model-service suppports batch
|
| 57 |
questions = ["what are the adverse reactions of Dimethylsulfoxide"]
|
| 58 |
sentences = ["Dimethylsulfoxide Adverse reactions Garlic taste in mouth, dry skin, erythema and pruritis (2), urine discoloration, halitosis, agitation, hypotension, sedation and dizziness (13) have been reported following use of DMSO. Dimethylsulfoxide Adverse reactions: malaria and loose motion."]
|
| 59 |
qa_sum_client_bart(questions, sentences)
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
pipeline_tag: question-answering
|
| 6 |
+
widget:
|
| 7 |
+
- text: >-
|
| 8 |
+
###Task: abstractive_qa
|
| 9 |
+
|
| 10 |
+
###Question: what are the adverse reactions of Dimethylsulfoxide
|
| 11 |
+
|
| 12 |
+
###Passages:Dimethylsulfoxide Adverse reactions Garlic taste in mouth, dry
|
| 13 |
+
skin, erythema and pruritis (2), urine discoloration, halitosis, agitation,
|
| 14 |
+
hypotension, sedation and dizziness (13) have been reported following use of
|
| 15 |
+
DMSO. Dimethylsulfoxide Adverse reactions: malaria and loose motion.
|
| 16 |
+
tags:
|
| 17 |
+
- rag
|
| 18 |
+
- question answering
|
| 19 |
+
- retrieval augmented generation
|
| 20 |
---
|
| 21 |
# Model Card for task-llm
|
| 22 |
|
| 23 |
This model supports abstractive QA tasks. Given a set of passages and a question, it tries to generate a comprehensive answer by reading the passages.
|
| 24 |
+
In other words, the model does the generation part of retrieval augmented generation (RAG).
|
| 25 |
|
| 26 |
## Model Details
|
| 27 |
|
|
|
|
| 68 |
url=v100Url,
|
| 69 |
retry=1,
|
| 70 |
)
|
| 71 |
+
# nlm-model-service suppports batch invocation and you can send multiple question/passage pairs at a time.
|
| 72 |
questions = ["what are the adverse reactions of Dimethylsulfoxide"]
|
| 73 |
sentences = ["Dimethylsulfoxide Adverse reactions Garlic taste in mouth, dry skin, erythema and pruritis (2), urine discoloration, halitosis, agitation, hypotension, sedation and dizziness (13) have been reported following use of DMSO. Dimethylsulfoxide Adverse reactions: malaria and loose motion."]
|
| 74 |
qa_sum_client_bart(questions, sentences)
|