Instructions to use LoupGarou/WizardCoder-Guanaco-15B-V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoupGarou/WizardCoder-Guanaco-15B-V1.0 with Transformers:

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

pipe = pipeline("text-generation", model="LoupGarou/WizardCoder-Guanaco-15B-V1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LoupGarou/WizardCoder-Guanaco-15B-V1.0")
model = AutoModelForCausalLM.from_pretrained("LoupGarou/WizardCoder-Guanaco-15B-V1.0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LoupGarou/WizardCoder-Guanaco-15B-V1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LoupGarou/WizardCoder-Guanaco-15B-V1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoupGarou/WizardCoder-Guanaco-15B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LoupGarou/WizardCoder-Guanaco-15B-V1.0

SGLang

How to use LoupGarou/WizardCoder-Guanaco-15B-V1.0 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 "LoupGarou/WizardCoder-Guanaco-15B-V1.0" \
    --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": "LoupGarou/WizardCoder-Guanaco-15B-V1.0",
		"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 "LoupGarou/WizardCoder-Guanaco-15B-V1.0" \
        --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": "LoupGarou/WizardCoder-Guanaco-15B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LoupGarou/WizardCoder-Guanaco-15B-V1.0 with Docker Model Runner:
```
docker model run hf.co/LoupGarou/WizardCoder-Guanaco-15B-V1.0
```

LoupGarou commited on Jul 9, 2023

Commit

ab5ea67

1 Parent(s): 4808647

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -10,12 +10,12 @@ license:
 ---
 ## WizardGuanaco-V1.0 Model Card
-The WizardCoder-Guanaco-15B-V1.0 is a language model that combines the strengths of the [WizardCoder](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0) base model and the [Guanaco](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset) dataset for finetuning. The Guanaco dataset is trimmed to within 2 standard deviations of token size for input and output pairs and all non-english data has been removed to reduce training size requirements.
 # Model Description
-This model is built on top of the WizardCoder base model, a large language model known for its impressive capabilities in code related instruction. The WizardCoder base model was further finetuned using QLORA on the Guanaco dataset to enhance its generative abilities.
-However, to ensure more targeted learning and data processing, the Guanaco dataset was trimmed to within 2 standard deviations of token size for question sets. This process enhances the model's ability to generate more precise and relevant answers, eliminating outliers that could potentially distort the responses. In addition, to focus on English language proficiency, all non-English data has been removed from the Guanaco dataset.
 # Intended Use
 This model is designed to be used for a wide array of text generation tasks that require understanding and generating English text. The model is expected to perform well in tasks such as answering questions, writing essays, summarizing text, translation, and more. However, given the specific data processing and finetuning done, it might be particularly effective for tasks related to English language question-answering systems.
@@ -70,10 +70,10 @@ if __name__ == "__main__":
 ```
 # Training Procedure
-The base WizardCoder model was finetuned on the Guanaco dataset using QLORA, which was trimmed to within 2 standard deviations of token size for question sets and randomized. All non-English data was also removed from this finetuning dataset.
 ## Acknowledgements
-This model, WizardCoder-Guanaco-15B-V1.0, is simply building on the efforts of two great teams to evaluate the performance of a combined model with the strengths of the [WizardCoder base model](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0) and the [Guanaco dataset](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset).
 A sincere appreciation goes out to the developers and the community involved in the creation and refinement of these models. Their commitment to providing open source tools and datasets have been instrumental in making this project a reality.

 ---
 ## WizardGuanaco-V1.0 Model Card
+The WizardCoder-Guanaco-15B-V1.0 is a language model that combines the strengths of the [WizardCoder](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0) base model and the [openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) dataset for finetuning. The openassistant-guanaco dataset was further trimmed to within 2 standard deviations of token size for input and output pairs and all non-english data has been removed to reduce training size requirements.
 # Model Description
+This model is built on top of the WizardCoder base model, a large language model known for its impressive capabilities in code related instruction. The WizardCoder base model was further finetuned using QLORA on the openassistant-guanaco dataset to enhance its generative abilities.
+However, to ensure more targeted learning and data processing, the dataset was trimmed to within 2 standard deviations of token size for question sets. This process enhances the model's ability to generate more precise and relevant answers, eliminating outliers that could potentially distort the responses. In addition, to focus on English language proficiency, all non-English data has been removed from the Guanaco dataset.
 # Intended Use
 This model is designed to be used for a wide array of text generation tasks that require understanding and generating English text. The model is expected to perform well in tasks such as answering questions, writing essays, summarizing text, translation, and more. However, given the specific data processing and finetuning done, it might be particularly effective for tasks related to English language question-answering systems.
 ```
 # Training Procedure
+The base WizardCoder model was finetuned on the openassistant-guanaco dataset using QLORA, which was trimmed to within 2 standard deviations of token size for question sets and randomized. All non-English data was also removed from this finetuning dataset.
 ## Acknowledgements
+This model, WizardCoder-Guanaco-15B-V1.0, is simply building on the efforts of two great teams to evaluate the performance of a combined model with the strengths of the [WizardCoder base model](https://huggingface.co/WizardLM/WizardCoder-15B-V1.0) and the [openassistant-guanaco dataset](https://huggingface.co/datasets/timdettmers/openassistant-guanaco).
 A sincere appreciation goes out to the developers and the community involved in the creation and refinement of these models. Their commitment to providing open source tools and datasets have been instrumental in making this project a reality.