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

Libraries

How to use solidrust/BeagleCatMunin-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/BeagleCatMunin-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/BeagleCatMunin-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/BeagleCatMunin-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solidrust/BeagleCatMunin-AWQ with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/solidrust/BeagleCatMunin-AWQ

SGLang

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

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

Suparious commited on May 2, 2024

Commit

0d3d485

verified ·

1 Parent(s): 01dcd4e

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -0

README.md CHANGED Viewed

@@ -1,12 +1,23 @@
 ---
 library_name: transformers
 tags:
 - 4-bit
 - AWQ
 - text-generation
 - autotrain_compatible
 - endpoints_compatible
 pipeline_tag: text-generation
 inference: false
 quantized_by: Suparious
 ---
@@ -15,7 +26,9 @@ quantized_by: Suparious
 - Model creator: [timpal0l](https://huggingface.co/timpal0l)
 - Original model: [BeagleCatMunin](https://huggingface.co/timpal0l/BeagleCatMunin)
 ## How to use

 ---
+language:
+- sv
+- da
+- 'no'
+- is
+- en
 library_name: transformers
+license: apache-2.0
 tags:
+- merge
 - 4-bit
 - AWQ
 - text-generation
 - autotrain_compatible
 - endpoints_compatible
 pipeline_tag: text-generation
+base_model:
+- timpal0l/Mistral-7B-v0.1-flashback-v2
+- RJuro/munin-neuralbeagle-7b-GGUF
 inference: false
 quantized_by: Suparious
 ---
 - Model creator: [timpal0l](https://huggingface.co/timpal0l)
 - Original model: [BeagleCatMunin](https://huggingface.co/timpal0l/BeagleCatMunin)
+![](https://huggingface.co/timpal0l/flashbeagle-7b/resolve/main/model_img.png?download=true)
+This model is a merge of [timpal0l/Mistral-7B-v0.1-flashback-v2](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2) and [RJuro/munin-neuralbeagle-7b](https://huggingface.co/RJuro/munin-neuralbeagle-7b).
 ## How to use