Instructions to use tangledgroup/tangled-alpha-0.12-core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tangledgroup/tangled-alpha-0.12-core with Transformers:

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

pipe = pipeline("text-generation", model="tangledgroup/tangled-alpha-0.12-core")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tangledgroup/tangled-alpha-0.12-core", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tangledgroup/tangled-alpha-0.12-core with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tangledgroup/tangled-alpha-0.12-core"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tangledgroup/tangled-alpha-0.12-core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tangledgroup/tangled-alpha-0.12-core

SGLang

How to use tangledgroup/tangled-alpha-0.12-core 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 "tangledgroup/tangled-alpha-0.12-core" \
    --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": "tangledgroup/tangled-alpha-0.12-core",
		"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 "tangledgroup/tangled-alpha-0.12-core" \
        --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": "tangledgroup/tangled-alpha-0.12-core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tangledgroup/tangled-alpha-0.12-core with Docker Model Runner:
```
docker model run hf.co/tangledgroup/tangled-alpha-0.12-core
```

tangled-alpha-0.12-core / scripts /backup /merge-core-into-base.yaml

mtasic85

pretrain

f1c3ec3 over 1 year ago

Raw History Blame

2.23 kB

	slices:
	# 1
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 2
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 3
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 4
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 5
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 6
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 7
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 8
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 9
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 10
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 11
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 12
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 13
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 14
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 15
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 16
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 17
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 18
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 19
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 20
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 21
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 22
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 23
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]
	# 24
	- sources:
	- model: ../out/pretrain-core-converted/
	layer_range: [0, 1]

	merge_method: passthrough
	dtype: bfloat16