Instructions to use Connorvr/BrightBot-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Connorvr/BrightBot-small with Transformers:

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

pipe = pipeline("text-generation", model="Connorvr/BrightBot-small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Connorvr/BrightBot-small")
model = AutoModelForCausalLM.from_pretrained("Connorvr/BrightBot-small")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Connorvr/BrightBot-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Connorvr/BrightBot-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Connorvr/BrightBot-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Connorvr/BrightBot-small

SGLang

How to use Connorvr/BrightBot-small 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 "Connorvr/BrightBot-small" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Connorvr/BrightBot-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Connorvr/BrightBot-small" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Connorvr/BrightBot-small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Connorvr/BrightBot-small with Docker Model Runner:
```
docker model run hf.co/Connorvr/BrightBot-small
```

Connorvr commited on Nov 11, 2021

Commit

c74836e

1 Parent(s): f489c43

Retrain on gender neutral data

Browse files

Files changed (4) hide show

eval_results.txt +1 -1
pytorch_model.bin +1 -1
training_args.bin +1 -1
training_data.csv +0 -0

eval_results.txt CHANGED Viewed

	@@ -1 +1 @@
1	- perplexity = tensor(1.~~0744~~)


1	+ perplexity = tensor(1.6352)

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06e86a1d4aa5bab2c597aba95c43a2ca7e07599dbfb2128d4f3436cd0de7fb61
 size 510403817

 version https://git-lfs.github.com/spec/v1
+oid sha256:acead3775bcc80b15f9d9a0c2af7e17109c87daeab341ef07a252d406c5c25ff
 size 510403817

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a3334a1d6a6a14967951c36e9007636922bd7362f61f7e6a7731ba460aa791
 size 1327

 version https://git-lfs.github.com/spec/v1
+oid sha256:9cc944ea6b2746fb620c1201cb14a3cec086bfeccd68159e9fb6306794692660
 size 1327

training_data.csv ADDED Viewed

The diff for this file is too large to render. See raw diff