Instructions to use apol/alia-40b-distill-vapol with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apol/alia-40b-distill-vapol with Transformers:

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

pipe = pipeline("text-generation", model="apol/alia-40b-distill-vapol")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("apol/alia-40b-distill-vapol", device_map="auto")

PEFT
How to use apol/alia-40b-distill-vapol with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use apol/alia-40b-distill-vapol with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "apol/alia-40b-distill-vapol"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apol/alia-40b-distill-vapol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/apol/alia-40b-distill-vapol

SGLang

How to use apol/alia-40b-distill-vapol 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 "apol/alia-40b-distill-vapol" \
    --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": "apol/alia-40b-distill-vapol",
		"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 "apol/alia-40b-distill-vapol" \
        --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": "apol/alia-40b-distill-vapol",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use apol/alia-40b-distill-vapol with Docker Model Runner:
```
docker model run hf.co/apol/alia-40b-distill-vapol
```

apol commited on May 1

Commit

37dbcdf

verified ·

1 Parent(s): 9142f0c

Add Q4_K_M GGUF transport chunk ALIA-40b-distill-vapol-Q4_K_M.gguf.part-045

Browse files

Files changed (2) hide show

.gitattributes +1 -0
ALIA-40b-distill-vapol-Q4_K_M.gguf.part-045 +3 -0

.gitattributes CHANGED Viewed

@@ -88,3 +88,4 @@ ALIA-40b-distill-vapol-Q4_K_M.gguf.part-041 filter=lfs diff=lfs merge=lfs -text
 ALIA-40b-distill-vapol-Q4_K_M.gguf.part-042 filter=lfs diff=lfs merge=lfs -text
 ALIA-40b-distill-vapol-Q4_K_M.gguf.part-043 filter=lfs diff=lfs merge=lfs -text
 ALIA-40b-distill-vapol-Q4_K_M.gguf.part-044 filter=lfs diff=lfs merge=lfs -text

 ALIA-40b-distill-vapol-Q4_K_M.gguf.part-042 filter=lfs diff=lfs merge=lfs -text
 ALIA-40b-distill-vapol-Q4_K_M.gguf.part-043 filter=lfs diff=lfs merge=lfs -text
 ALIA-40b-distill-vapol-Q4_K_M.gguf.part-044 filter=lfs diff=lfs merge=lfs -text
+ALIA-40b-distill-vapol-Q4_K_M.gguf.part-045 filter=lfs diff=lfs merge=lfs -text

ALIA-40b-distill-vapol-Q4_K_M.gguf.part-045 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:863ca0dee7dca3bd7b7ac3b3445ff3ee95ddb9647856f37cde3a584988292f36
+size 432347552