Instructions to use tangledgroup/tangled-alpha-0.11-core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tangledgroup/tangled-alpha-0.11-core with Transformers:

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

pipe = pipeline("text-generation", model="tangledgroup/tangled-alpha-0.11-core")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tangledgroup/tangled-alpha-0.11-core", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tangledgroup/tangled-alpha-0.11-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-0.11-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-0.11-core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tangledgroup/tangled-alpha-0.11-core

SGLang

How to use tangledgroup/tangled-alpha-0.11-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-0.11-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-0.11-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-0.11-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-0.11-core",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tangledgroup/tangled-alpha-0.11-core with Docker Model Runner:
```
docker model run hf.co/tangledgroup/tangled-alpha-0.11-core
```

tangled-alpha-0.11-core / scripts /backup /pretrain_reflection_datasets.py

mtasic85

pretrain

26a07d4 about 1 year ago

raw

history blame contribute delete

1.37 kB

	roles_map = {
	'system': 'system',
	'user': 'user',
	'human': 'user',
	'assistant': 'assistant',
	'gpt': 'assistant',
	'AI': 'assistant',
	}


	pretrain_reflection_datasets = [
	#
	# reflection
	#
	# 4.17 MB, 1,000
	{'kind': 'instruct', 'path': 'dvilasuero/reflection-v1-gpt-4o-judge', 'transform': lambda r: [
	{'role': 'system', 'content': r['system']},
	{'role': 'user', 'content': r['prompt']},
	{'role': 'assistant', 'content': r['response']},
	]},
	# 12.4 MB, 3,000
	{'kind': 'instruct', 'path': 'dvilasuero/reflection-v1-openai-o-mini-judge', 'transform': lambda r: [
	{'role': 'system', 'content': r['system']},
	{'role': 'user', 'content': r['prompt']},
	{'role': 'assistant', 'content': r['response']},
	]},
	# 70.8 MB, 36,549
	{'kind': 'instruct', 'path': 'dvilasuero/reflection-v1-final-dedup', 'transform': lambda r: [
	{'role': 'system', 'content': r['system']},
	{'role': 'user', 'content': r['prompt']},
	{'role': 'assistant', 'content': r['response']},
	]},
	# 30.6 MB, 25,391
	{'kind': 'instruct', 'path': 'flozi00/reflection-qwen2.5-72b-260924', 'transform': lambda r: [
	r['system'][0],
	{'role': 'user', 'content': r['input']},
	{'role': 'assistant', 'content': r['reflection'] + '\n' + r['output']},
	]},
	]