Instructions to use tangledgroup/tangled-alpha-0.1-core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tangledgroup/tangled-alpha-0.1-core with Transformers:

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

pipe = pipeline("text-generation", model="tangledgroup/tangled-alpha-0.1-core")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tangledgroup/tangled-alpha-0.1-core", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tangledgroup/tangled-alpha-0.1-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-0.1-core"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tangledgroup/tangled-alpha-0.1-core",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tangledgroup/tangled-alpha-0.1-core

SGLang

How to use tangledgroup/tangled-alpha-0.1-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-0.1-core" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tangledgroup/tangled-alpha-0.1-core",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-0.1-core" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tangledgroup/tangled-alpha-0.1-core",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tangledgroup/tangled-alpha-0.1-core with Docker Model Runner:
```
docker model run hf.co/tangledgroup/tangled-alpha-0.1-core
```

tangled-alpha-0.1-core / README.md

mtasic85

micro_batch_size: 4

50de401 over 1 year ago

preview code

Raw

History Blame

5.28 kB

	---
	license: mit
	pipeline_tag: text-generation
	library_name: transformers
	language: [
	'en', 'am', 'ar', 'as', 'az', 'be', 'bg', 'bn', 'br', 'bs', 'ca', 'cs', 'cy', 'da', 'de', 'el',
	'eo', 'es', 'et', 'eu', 'fa', 'ff', 'fi', 'fr', 'fy', 'ga', 'gd', 'gl', 'gn', 'gu', 'ha', 'he',
	'hi', 'hr', 'ht', 'hu', 'hy', 'id', 'ig', 'is', 'it', 'ja', 'jv', 'ka', 'kk', 'km', 'kn', 'ko',
	'ku', 'ky', 'la', 'lg', 'li', 'ln', 'lo', 'lt', 'lv', 'mg', 'mk', 'ml', 'mn', 'mr', 'ms', 'my',
	'ne', 'nl', 'no', 'ns', 'om', 'or', 'pa', 'pl', 'ps', 'pt', 'qu', 'rm', 'ro', 'ru', 'sa', 'si',
	'sc', 'sd', 'sk', 'sl', 'so', 'sq', 'sr', 'ss', 'su', 'sv', 'sw', 'ta', 'te', 'th', 'tl', 'tn',
	'tr', 'ug', 'uk', 'ur', 'uz', 'vi', 'wo', 'xh', 'yi', 'yo', 'zu',
	]
	datasets:
	# core - base
	- ontocord/fineweb-permissive-multilingual-2m
	- distily/c4_multilingual_1M
	- data-silence/sumnews
	- xu-song/cc100-samples
	- badrex/llm-emoji-dataset
	- fblgit/simple-math
	- Gusarich/math-expressions-1m
	- neuralwork/arxiver
	- christopher/rosetta-code
	- nampdn-ai/tiny-codes
	- JeanKaddour/minipile
	# core - instruct
	- NousResearch/hermes-function-calling-v1
	- simplescaling/s1K-1.1
	# base - instruct
	- mlabonne/open-perfectblend
	- allenai/tulu-3-sft-mixture
	- rombodawg/Everything_Instruct_Multilingual
	# base - reason
	- open-r1/OpenR1-Math-220k
	- open-thoughts/OpenThoughts-114k
	- cognitivecomputations/dolphin-r1
	- simplescaling/s1K-1.1
	tags:
	- chat
	- core
	- base
	- instruct
	- reason
	---

	# tangled-alpha-0.1-core

	![logo](./misc/logo.jpg)

	```bash
	time python -B prepare_core_datasets.py
	```

	```
	Progress: 100%\|████████\| 220/220 [23:15<00:00, 6.34s/it]
	Workers are finished.██\| 220/220 [23:15<00:00, 6.34s/it]
	Finished data processing!
	i=0, block_size=8192, chunk_size=16384000, len(dataset)=893355, len(dataset) * block_size=7318364160
	Total number of tokens in the optimized dataset '../core-data-0-8192-2000' is 7318364160
	```

	```bash
	CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt pretrain --config pretrain-core-model.yaml
	```

	```
	Seed set to 23
	Time to instantiate model: 0.23 seconds.
	Total parameters: 138,084,864
	Verifying settings ...
	Measured TFLOPs: 6972.54
	Epoch 1 \| iter 256 step 1 \| loss train: 10.530, val: n/a \| iter time: 3230.47 ms (step) remaining time: 3 days, 5:34:13
	Epoch 1 \| iter 512 step 2 \| loss train: 10.520, val: n/a \| iter time: 589.19 ms (step) remaining time: 3 days, 0:40:40
	Epoch 1 \| iter 768 step 3 \| loss train: 10.485, val: n/a \| iter time: 591.81 ms (step) remaining time: 2 days, 23:01:54
	Epoch 1 \| iter 1024 step 4 \| loss train: 10.447, val: n/a \| iter time: 589.35 ms (step) remaining time: 2 days, 22:11:32
	Epoch 1 \| iter 1280 step 5 \| loss train: 10.350, val: n/a \| iter time: 589.38 ms (step) remaining time: 2 days, 21:40:13
	Epoch 1 \| iter 1536 step 6 \| loss train: 10.241, val: n/a \| iter time: 593.75 ms (step) remaining time: 2 days, 21:18:19
	Epoch 1 \| iter 1792 step 7 \| loss train: 10.134, val: n/a \| iter time: 592.92 ms (step) remaining time: 2 days, 21:01:58
	Epoch 1 \| iter 2048 step 8 \| loss train: 10.049, val: n/a \| iter time: 590.74 ms (step) remaining time: 2 days, 20:49:12
	Epoch 1 \| iter 2304 step 9 \| loss train: 9.869, val: n/a \| iter time: 594.27 ms (step) remaining time: 2 days, 20:39:10
	Epoch 1 \| iter 2560 step 10 \| loss train: 9.771, val: n/a \| iter time: 590.04 ms (step) remaining time: 2 days, 20:30:14
	Epoch 1 \| iter 2816 step 11 \| loss train: 9.643, val: n/a \| iter time: 588.32 ms (step) remaining time: 2 days, 20:22:22
	Epoch 1 \| iter 3072 step 12 \| loss train: 9.557, val: n/a \| iter time: 588.95 ms (step) remaining time: 2 days, 20:15:26
	Epoch 1 \| iter 3328 step 13 \| loss train: 9.487, val: n/a \| iter time: 589.32 ms (step) remaining time: 2 days, 20:09:05
	Epoch 1 \| iter 3584 step 14 \| loss train: 9.413, val: n/a \| iter time: 588.95 ms (step) remaining time: 2 days, 20:03:24
	Epoch 1 \| iter 3840 step 15 \| loss train: 9.322, val: n/a \| iter time: 591.62 ms (step) remaining time: 2 days, 19:58:18
	Epoch 1 \| iter 4096 step 16 \| loss train: 9.241, val: n/a \| iter time: 593.65 ms (step) remaining time: 2 days, 19:53:30
	Epoch 1 \| iter 4352 step 17 \| loss train: 9.163, val: n/a \| iter time: 593.89 ms (step) remaining time: 2 days, 19:49:00
	Epoch 1 \| iter 4608 step 18 \| loss train: 9.122, val: n/a \| iter time: 590.63 ms (step) remaining time: 2 days, 19:44:42
	Epoch 1 \| iter 4864 step 19 \| loss train: 9.077, val: n/a \| iter time: 590.87 ms (step) remaining time: 2 days, 19:40:47
	Epoch 1 \| iter 5120 step 20 \| loss train: 9.018, val: n/a \| iter time: 588.44 ms (step) remaining time: 2 days, 19:36:59
	# ...
	```

	Backup `wandb`:

	```bash
	mv wandb wandb-pretrain-core
	```

	Chat with model:

	```bash
	CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True litgpt chat ../out/pretrain-core/final
	```

	```bash
	CUDA_VISIBLE_DEVICES=0 CUDA_LAUNCH_BLOCKING=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True time litgpt evaluate --tasks 'leaderboard' --out_dir '../evaluate/pretrain-core/leaderboard/' --batch_size 1 --dtype 'bfloat16' '../out/pretrain-core/final'
	```

	```
	# ...
	```