Instructions to use brandolorian/answerQuestioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brandolorian/answerQuestioning with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="brandolorian/answerQuestioning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brandolorian/answerQuestioning")
model = AutoModelForCausalLM.from_pretrained("brandolorian/answerQuestioning")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use brandolorian/answerQuestioning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brandolorian/answerQuestioning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brandolorian/answerQuestioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/brandolorian/answerQuestioning

SGLang

How to use brandolorian/answerQuestioning 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 "brandolorian/answerQuestioning" \
    --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": "brandolorian/answerQuestioning",
		"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 "brandolorian/answerQuestioning" \
        --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": "brandolorian/answerQuestioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use brandolorian/answerQuestioning with Docker Model Runner:
```
docker model run hf.co/brandolorian/answerQuestioning
```

brandolorian commited on Feb 19, 2024

Commit

3bd1654

verified ·

1 Parent(s): cf6b640

Training in progress, step 500

Browse files

Files changed (4) hide show

config.json +1 -1
model.safetensors +1 -1
runs/Feb19_02-21-19_61a4bf2b3b7a/events.out.tfevents.1708309281.61a4bf2b3b7a.781.0 +3 -0
training_args.bin +2 -2

config.json CHANGED Viewed

@@ -40,7 +40,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 50257,
   "window_size": 256

   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
   "use_cache": true,
   "vocab_size": 50257,
   "window_size": 256

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57eb1e102753485669bd3df9a4a8efe8aa7c01eb30c3e57be1f1e3083907bdc7
 size 274062040

 version https://git-lfs.github.com/spec/v1
+oid sha256:2950286dbbd6a135090a8e040a229cbe539550bde24f050dd02e1a77841dcee9
 size 274062040

runs/Feb19_02-21-19_61a4bf2b3b7a/events.out.tfevents.1708309281.61a4bf2b3b7a.781.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:92412aae35eccd125fee245816f476eaeb433323aae16a87505770ce2dfdb6f2
+size 5083

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb69b40310857fcdd5a445da4b7f0b76d8325d7b185323a382c7f69a068f91cd
-size 4728

 version https://git-lfs.github.com/spec/v1
+oid sha256:139b2777fbc590bc6e6a556597af150e7955f09cbd05ba59d20639342d786f51
+size 4920