Instructions to use Tincando/Poe_Cerebras_try2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tincando/Poe_Cerebras_try2 with Transformers:

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

pipe = pipeline("text-generation", model="Tincando/Poe_Cerebras_try2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tincando/Poe_Cerebras_try2")
model = AutoModelForCausalLM.from_pretrained("Tincando/Poe_Cerebras_try2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tincando/Poe_Cerebras_try2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tincando/Poe_Cerebras_try2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tincando/Poe_Cerebras_try2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tincando/Poe_Cerebras_try2

SGLang

How to use Tincando/Poe_Cerebras_try2 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 "Tincando/Poe_Cerebras_try2" \
    --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": "Tincando/Poe_Cerebras_try2",
		"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 "Tincando/Poe_Cerebras_try2" \
        --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": "Tincando/Poe_Cerebras_try2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tincando/Poe_Cerebras_try2 with Docker Model Runner:
```
docker model run hf.co/Tincando/Poe_Cerebras_try2
```

Tincando commited on Apr 13, 2023

Commit

ecca165

1 Parent(s): e81ebab

Training in progress, step 2500

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Apr13_11-02-25_e788ad981b23/events.out.tfevents.1681383782.e788ad981b23.257.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283a6bec4152a8815238183ca1d1685d4a0669185ba84ba72b612fbcc7dbe3c8
 size 2436824525

 version https://git-lfs.github.com/spec/v1
+oid sha256:f07eee01e2d050f13e50fb302a520f4531520dc1801ac6a7b79bc610adc983f1
 size 2436824525

runs/Apr13_11-02-25_e788ad981b23/events.out.tfevents.1681383782.e788ad981b23.257.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e298d7b92a3ee51fda4e8675d610ac4765cf4c22de729d032e9b6da9c3d6c230
-size 4667

 version https://git-lfs.github.com/spec/v1
+oid sha256:64f61b6d3bbb299fd28aa9785711425eb2519c16c78e8d378a1f0b59d899f140
+size 4824