Instructions to use MD1998/chating_beginner_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MD1998/chating_beginner_v3 with Transformers:

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

pipe = pipeline("text-generation", model="MD1998/chating_beginner_v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("MD1998/chating_beginner_v3")
model = AutoModelForSeq2SeqLM.from_pretrained("MD1998/chating_beginner_v3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MD1998/chating_beginner_v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MD1998/chating_beginner_v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MD1998/chating_beginner_v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MD1998/chating_beginner_v3

SGLang

How to use MD1998/chating_beginner_v3 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 "MD1998/chating_beginner_v3" \
    --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": "MD1998/chating_beginner_v3",
		"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 "MD1998/chating_beginner_v3" \
        --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": "MD1998/chating_beginner_v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MD1998/chating_beginner_v3 with Docker Model Runner:
```
docker model run hf.co/MD1998/chating_beginner_v3
```

MD1998 commited on Apr 29, 2024

Commit

cdbf1a0

verified ·

1 Parent(s): cdacf44

Training in progress, step 2000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Apr29_11-01-27_ba52a902ab8f/events.out.tfevents.1714388501.ba52a902ab8f.777.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8667a03128365fa2c7f4a9bc9bb2b07b1f5e36467f09f8d56e5f89e6cea1fb8e
 size 990345064

 version https://git-lfs.github.com/spec/v1
+oid sha256:a4255b8f4a11baca4e3718dc56481a86e6b67ce04f0792264aa12be076719012
 size 990345064

runs/Apr29_11-01-27_ba52a902ab8f/events.out.tfevents.1714388501.ba52a902ab8f.777.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a597090ddb53760141b1bc8fb1004cf205cec8241b5272ef7227330bdaa87dc4
-size 8239

 version https://git-lfs.github.com/spec/v1
+oid sha256:6b0ac72e53b69478ff0f9e046a223385acce80362c7733c4661fffee36f7a56a
+size 8924