talkmap/banking-conversation-corpus
Viewer β’ Updated β’ 5.53M β’ 155 β’ 15
How to use AmjadKha/Boppy with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="AmjadKha/Boppy") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("AmjadKha/Boppy")
model = AutoModelForCausalLM.from_pretrained("AmjadKha/Boppy")How to use AmjadKha/Boppy with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AmjadKha/Boppy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "AmjadKha/Boppy",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/AmjadKha/Boppy
How to use AmjadKha/Boppy with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "AmjadKha/Boppy" \
--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": "AmjadKha/Boppy",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "AmjadKha/Boppy" \
--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": "AmjadKha/Boppy",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use AmjadKha/Boppy with Docker Model Runner:
docker model run hf.co/AmjadKha/Boppy
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("AmjadKha/Boppy")
model = AutoModelForCausalLM.from_pretrained("AmjadKha/Boppy")I have created a text-generation model named Boppy, designed to assist as a company agent or customer service representative. I am now beginning the process of training Boppy to interact with customers in accordance with company policy.π©π»βπ»
Python, HTML, CSS, Springboot
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AmjadKha/Boppy")