Instructions to use TheBloke/OpenZephyrChat-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/OpenZephyrChat-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/OpenZephyrChat-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/OpenZephyrChat-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/OpenZephyrChat-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheBloke/OpenZephyrChat-AWQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TheBloke/OpenZephyrChat-AWQ

SGLang

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

Docker Model Runner
How to use TheBloke/OpenZephyrChat-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/OpenZephyrChat-AWQ
```

TheBloke commited on Dec 13, 2023

Commit

f7570ac

1 Parent(s): f82599e

Upload README.md

Browse files

Files changed (1) hide show

README.md +9 -4

README.md CHANGED Viewed

@@ -354,15 +354,20 @@ And thank you again to a16z for their generous grant.
   <img src="https://huggingface.co/Fredithefish/OpenZephyrChat/resolve/main/logo.jpeg" alt="Alt Text" width="250"/>
   <h1>🔥 OpenZephyrChat - Merging Zephyr-beta with OpenChat-3.5 🔥</h1>
-  This Model is a merge between Zephyr-beta and OpenChat-3.5, it was done by using the <a>https://github.com/cg123/mergekit</a> repository
 </div>
 # Model Information
 - **Parameter size:** 7B
-- **Datasets:**
-  - Please take a look at the individual model pages of OpenChat and Zephyr.
 ## Evals
 <table>

   <img src="https://huggingface.co/Fredithefish/OpenZephyrChat/resolve/main/logo.jpeg" alt="Alt Text" width="250"/>
   <h1>🔥 OpenZephyrChat - Merging Zephyr-beta with OpenChat-3.5 🔥</h1>
+  This Model is a ties merge between Zephyr-beta and OpenChat-3.5, it was done by using the <a>https://github.com/cg123/mergekit</a> repository
 </div>
 # Model Information
+- **License:** Apache-2 (commercially usable)
 - **Parameter size:** 7B
+- **Merge:**
+  - [OpenChat](https://huggingface.co/openchat/openchat_3.5) with ```--weight 0.6 --density 0.5```
+  - [Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) with ```--weight 0.3 --density 0.5```
+  - [Mistral](https://huggingface.co/mistralai/Mistral-7B-v0.1) serving as the base model
 ## Evals
 <table>