Instructions to use Osquery/eli5_clm-model-2007 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Osquery/eli5_clm-model-2007 with Transformers:

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

pipe = pipeline("text-generation", model="Osquery/eli5_clm-model-2007")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Osquery/eli5_clm-model-2007")
model = AutoModelForCausalLM.from_pretrained("Osquery/eli5_clm-model-2007")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Osquery/eli5_clm-model-2007 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Osquery/eli5_clm-model-2007"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Osquery/eli5_clm-model-2007",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Osquery/eli5_clm-model-2007

SGLang

How to use Osquery/eli5_clm-model-2007 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 "Osquery/eli5_clm-model-2007" \
    --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": "Osquery/eli5_clm-model-2007",
		"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 "Osquery/eli5_clm-model-2007" \
        --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": "Osquery/eli5_clm-model-2007",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Osquery/eli5_clm-model-2007 with Docker Model Runner:
```
docker model run hf.co/Osquery/eli5_clm-model-2007
```

Osquery commited on Dec 3, 2023

Commit

1bfe221

1 Parent(s): fc8566e

Training in progress, step 1500

Browse files

Files changed (3) hide show

model.safetensors +1 -1
runs/Dec02_21-36-26_MSI/events.out.tfevents.1701581787.MSI.167383.7 +3 -0
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa6e71620f6fb96350dc454ddc9394772dd2d7d23360bd067840dc48e77d9a2
 size 327657928

 version https://git-lfs.github.com/spec/v1
+oid sha256:7bb0ec11fdf16944e2cce6cd7f815e3f68554278db8d68b9d1b36d575e31d7d6
 size 327657928

runs/Dec02_21-36-26_MSI/events.out.tfevents.1701581787.MSI.167383.7 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd54ed242a523c503b67e3c4ed2be2f7772e39486fb6885062c449216cb89c6
+size 5395

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25984a2c88ca6da788b1127c324dace114646f994b2518356ff9485406280f5b
 size 4664

 version https://git-lfs.github.com/spec/v1
+oid sha256:715689eb083ec4a19e9f85d30f4f1fecae95964d58997854a70bf8ccaab9a172
 size 4664