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

Libraries

How to use cphienanda/nqaasksciencemodeling with Transformers:

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

pipe = pipeline("text-generation", model="cphienanda/nqaasksciencemodeling")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cphienanda/nqaasksciencemodeling")
model = AutoModelForCausalLM.from_pretrained("cphienanda/nqaasksciencemodeling")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cphienanda/nqaasksciencemodeling with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/cphienanda/nqaasksciencemodeling

SGLang

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

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

cphienanda commited on Dec 6, 2024

Commit

8931f5a

verified ·

1 Parent(s): 96c8acf

Training in progress, step 500

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Dec05_17-54-01_xtaco/events.out.tfevents.1733450042.xtaco.8356.8 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccf5da3b2dd8de964327c04deb36f6339a65b502e9a2c3ce8f2c89fec533760
 size 497774208

 version https://git-lfs.github.com/spec/v1
+oid sha256:843a2e793a1ad3814461caf9e14e3d359467eb04ec406fc62a8a7baf1b835dc2
 size 497774208

runs/Dec05_17-54-01_xtaco/events.out.tfevents.1733450042.xtaco.8356.8 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2cc42320463d3e46c145083ebd7675826dfd495dad8cb7dcbdbbf7d791e6f8d
-size 12265

 version https://git-lfs.github.com/spec/v1
+oid sha256:3aa828cde222f3dcf1e361dde177e5a8fdc203fe02d317bc24ee2f0aba77785e
+size 18131