Instructions to use yava-code/Tessera-1B-Nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yava-code/Tessera-1B-Nano with Transformers:

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

pipe = pipeline("text-generation", model="yava-code/Tessera-1B-Nano", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("yava-code/Tessera-1B-Nano", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yava-code/Tessera-1B-Nano with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yava-code/Tessera-1B-Nano"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yava-code/Tessera-1B-Nano",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yava-code/Tessera-1B-Nano

SGLang

How to use yava-code/Tessera-1B-Nano 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 "yava-code/Tessera-1B-Nano" \
    --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": "yava-code/Tessera-1B-Nano",
		"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 "yava-code/Tessera-1B-Nano" \
        --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": "yava-code/Tessera-1B-Nano",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yava-code/Tessera-1B-Nano with Docker Model Runner:
```
docker model run hf.co/yava-code/Tessera-1B-Nano
```

Tessera-1B-Nano / eval.json

yava-code

Publish Tessera-1B-Nano checkpoint

eb46968 verified 8 days ago

Raw History Blame Contribute Delete

1.15 kB

	{
	"intervention": {
	"shuffle_minus_predicted": 0.0008374229073524475,
	"zero_minus_predicted": 0.10504236817359924
	},
	"predicted": {
	"codebook_perplexity": 7.5476508140563965,
	"codebook_usage": 0.856249988079071,
	"loss_by_chunk_offset": {
	"0": 2.5110912322998047,
	"1": 2.520437240600586,
	"2": 2.5094692707061768,
	"3": 2.515815258026123
	},
	"ntp_loss": 2.5142061039805412,
	"perplexity": 12.356794873753902
	},
	"shuffle": {
	"codebook_perplexity": 7.5476508140563965,
	"codebook_usage": 0.856249988079071,
	"loss_by_chunk_offset": {
	"0": 2.5119338035583496,
	"1": 2.5215582847595215,
	"2": 2.5100176334381104,
	"3": 2.5166521072387695
	},
	"ntp_loss": 2.5150435268878937,
	"perplexity": 12.367147070821142
	},
	"zero": {
	"codebook_perplexity": 7.5476508140563965,
	"codebook_usage": 0.856249988079071,
	"loss_by_chunk_offset": {
	"0": 2.61773681640625,
	"1": 2.6253929138183594,
	"2": 2.6141862869262695,
	"3": 2.619673013687134
	},
	"ntp_loss": 2.6192484721541405,
	"perplexity": 13.725404684277025
	}
	}