Instructions to use macadeliccc/piccolo-2x7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macadeliccc/piccolo-2x7b with Transformers:

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

pipe = pipeline("text-generation", model="macadeliccc/piccolo-2x7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("macadeliccc/piccolo-2x7b")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/piccolo-2x7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use macadeliccc/piccolo-2x7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "macadeliccc/piccolo-2x7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "macadeliccc/piccolo-2x7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/macadeliccc/piccolo-2x7b

SGLang

How to use macadeliccc/piccolo-2x7b 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 "macadeliccc/piccolo-2x7b" \
    --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": "macadeliccc/piccolo-2x7b",
		"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 "macadeliccc/piccolo-2x7b" \
        --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": "macadeliccc/piccolo-2x7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use macadeliccc/piccolo-2x7b with Docker Model Runner:
```
docker model run hf.co/macadeliccc/piccolo-2x7b
```

macadeliccc commited on Jan 16, 2024

Commit

1fb50e7

verified ·

1 Parent(s): 70105d3

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -1

README.md CHANGED Viewed

@@ -48,4 +48,15 @@ The model is capable of quality code, math, and logical reasoning. Try whatever
 # Evaluations
-TODO

 # Evaluations
+|  Tasks   |Version|Filter|n-shot| Metric |Value |   |Stderr|
+|----------|-------|------|-----:|--------|-----:|---|-----:|
+|arc_easy  |Yaml   |none  |     0|acc     |0.8552|±  |0.0072|
+|          |       |none  |     0|acc_norm|0.8237|±  |0.0078|
+|boolq     |Yaml   |none  |     0|acc     |0.8749|±  |0.0058|
+|hellaswag |Yaml   |none  |     0|acc     |0.6734|±  |0.0047|
+|          |       |none  |     0|acc_norm|0.8489|±  |0.0036|
+|openbookqa|Yaml   |none  |     0|acc     |0.3640|±  |0.0215|
+|          |       |none  |     0|acc_norm|0.4780|±  |0.0224|
+|piqa      |Yaml   |none  |     0|acc     |0.8330|±  |0.0087|
+|          |       |none  |     0|acc_norm|0.8368|±  |0.0086|
+|winogrande|Yaml   |none  |     0|acc     |0.7703|±  |0.0118|