Instructions to use TildeAI/TildeOpen-30b-64k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TildeAI/TildeOpen-30b-64k with Transformers:

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

pipe = pipeline("text-generation", model="TildeAI/TildeOpen-30b-64k", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TildeAI/TildeOpen-30b-64k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TildeAI/TildeOpen-30b-64k", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TildeAI/TildeOpen-30b-64k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TildeAI/TildeOpen-30b-64k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TildeAI/TildeOpen-30b-64k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TildeAI/TildeOpen-30b-64k

SGLang

How to use TildeAI/TildeOpen-30b-64k 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 "TildeAI/TildeOpen-30b-64k" \
    --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": "TildeAI/TildeOpen-30b-64k",
		"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 "TildeAI/TildeOpen-30b-64k" \
        --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": "TildeAI/TildeOpen-30b-64k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TildeAI/TildeOpen-30b-64k with Docker Model Runner:
```
docker model run hf.co/TildeAI/TildeOpen-30b-64k
```

TildeOpen-30b-64k

Commit History

update code snippets

e4c6ad4

Martins Kronis commited on Apr 17

add model config

695086a

Martins Kronis commited on Apr 17

add YaRN patch for transformers 4x

a66e9c6

Martins Kronis commited on Apr 17

Add tokenizer files with LFS

0a98506

Martins Kronis commited on Apr 17

add model weights

40384dc

Martins Kronis commited on Apr 16

Update README.md

8505b0b
verified

mkronis commited on Apr 16

Update README.md

d4f6ef4
verified

mkronis commited on Apr 16

Update README.md

e3b4f7a
verified

mkronis commited on Apr 16

Update README.md

fb2e376
verified

mkronis commited on Apr 16

Update README.md

62ed0ff
verified

TBergmanis commited on Apr 16

Update README.md

38bd281
verified

TBergmanis commited on Apr 16

needle plots

bd99ee4

Martins Kronis commited on Apr 16

add model card

2ef0a00

Martins Kronis commited on Apr 16

initial commit

9ff4d15
verified

TildeSIA commited on Feb 4

Commit History

update code snippets e4c6ad4

add model config 695086a

add YaRN patch for transformers 4x a66e9c6

Add tokenizer files with LFS 0a98506

add model weights 40384dc

Update README.md 8505b0b verified

Update README.md d4f6ef4 verified

Update README.md e3b4f7a verified

Update README.md fb2e376 verified

Update README.md 62ed0ff verified

Update README.md 38bd281 verified

needle plots bd99ee4

add model card 2ef0a00

initial commit 9ff4d15 verified

update code snippets

e4c6ad4

add model config

695086a

add YaRN patch for transformers 4x

a66e9c6

Add tokenizer files with LFS

0a98506

add model weights

40384dc

Update README.md

8505b0b
verified

Update README.md

d4f6ef4
verified

Update README.md

e3b4f7a
verified

Update README.md

fb2e376
verified

Update README.md

62ed0ff
verified

Update README.md

38bd281
verified

needle plots

bd99ee4

add model card

2ef0a00

initial commit

9ff4d15
verified