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

c628292

verified ·

1 Parent(s): 02ba0e2

Add v20 adapter tokenizer config

Browse files

Files changed (1) hide show

adapter-candidates/dpo_v20_corrective_from_sft_custom/tokenizer_config.json +17 -0

adapter-candidates/dpo_v20_corrective_from_sft_custom/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 163840,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}