Instructions to use pankajmathur/orca_mini_3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/orca_mini_3b with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/orca_mini_3b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/orca_mini_3b")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/orca_mini_3b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pankajmathur/orca_mini_3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/orca_mini_3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajmathur/orca_mini_3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/orca_mini_3b

SGLang

How to use pankajmathur/orca_mini_3b 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 "pankajmathur/orca_mini_3b" \
    --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": "pankajmathur/orca_mini_3b",
		"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 "pankajmathur/orca_mini_3b" \
        --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": "pankajmathur/orca_mini_3b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/orca_mini_3b with Docker Model Runner:
```
docker model run hf.co/pankajmathur/orca_mini_3b
```

psmathur commited on Jun 24, 2023

Commit

7c09fc9

1 Parent(s): 17b2ccf

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -5

README.md CHANGED Viewed

@@ -3,20 +3,27 @@ license: mit
 language:
 - en
 library_name: transformers
 ---
-# Wizardlm Alpaca Dolly Orca Open_LLaMa_3b
-An Open_LLaMA-3B model trained on custom explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
 # Dataset
-We trained [OpenLLaMa-3B model](https://github.com/openlm-research/open_llama) on custom explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html)  & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
 We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
-This helps student model aka [wizardlm_alpaca_dolly_orca_open_llama_3b](https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_3b) to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
-Please see below example usage how the **System** prompt is added before each *instruction*.
 # Training

 language:
 - en
 library_name: transformers
+datasets:
+- psmathur/alpaca_orca
+- psmathur/dolly-v2_orca
+- psmathur/WizardLM_Orca
 ---
+# orca_mini_3b
+An [OpenLLaMa-3B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
 # Dataset
+We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html)  & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
 We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
+This helps student model aka [wizardlm_alpaca_dolly_orca_open_llama_13b](https://huggingface.co/psmathur/wizardlm_alpaca_dolly_orca_open_llama_13b) to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
+Please see below example usage how the **System** prompt is added before each **instruction**.
 # Training