Instructions to use Lernex/Metis-1.6-Logos-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lernex/Metis-1.6-Logos-Base with Transformers:

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

pipe = pipeline("text-generation", model="Lernex/Metis-1.6-Logos-Base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Lernex/Metis-1.6-Logos-Base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Lernex/Metis-1.6-Logos-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lernex/Metis-1.6-Logos-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lernex/Metis-1.6-Logos-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Lernex/Metis-1.6-Logos-Base

SGLang

How to use Lernex/Metis-1.6-Logos-Base 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 "Lernex/Metis-1.6-Logos-Base" \
    --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": "Lernex/Metis-1.6-Logos-Base",
		"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 "Lernex/Metis-1.6-Logos-Base" \
        --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": "Lernex/Metis-1.6-Logos-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lernex/Metis-1.6-Logos-Base with Docker Model Runner:
```
docker model run hf.co/Lernex/Metis-1.6-Logos-Base
```

Metis-1.6-Logos-Base

Commit History

Oct 30 3 days ago

02:09
Link the technical report on arXiv⁠

GiuliannoV

Verified signature
da7f090

Oct 28 5 days ago

00:52
Redraw the architecture figure as a block diagram

GiuliannoV

Verified signature
44a20b3

Oct 27 6 days ago

23:05
Redraw the architecture figure for the card width

GiuliannoV

Verified signature
9ce85f6
22:30
New architecture figure and a short note

GiuliannoV

Verified signature
3deab87
21:29
Benchmark table first

GiuliannoV

Verified signature
df4991c
21:24
Benchmark table first; Lernex on X is @Lernex_ai

GiuliannoV

Verified signature
7e34437
21:12
Release card and Transformers support⁠

GiuliannoV

Verified signature
084c9e3
20:28
Release under the Apache 2.0 license

GiuliannoV

Verified signature
489709b
09:34
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
39aed40
09:34
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
cdf3690
08:14
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
bf0d458
08:14
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
9a4bd2a
08:07
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
edd46df
08:07
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
019407f
07:47
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
64cca3a
07:47
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
9fdacd3
07:38
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
ecab5c7
07:38
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
45dc8c3
07:34
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
14aab48
07:34
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
3618426
07:32
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
2e10cb8
07:32
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
ac6de1c
07:30
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
aad36c3
07:30
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
98f6d1b
07:27
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
be2d4db
07:27
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
9a60670
07:25
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
5371a75
07:25
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
a11acaf
07:20
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
bf2e47b
07:20
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
6a17736
07:17
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
cb97c7b
07:17
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
0b0226e
07:14
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
3ef4f11
07:13
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
0e4aa66
07:12
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
ab09112
07:12
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
2338089
07:09
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
32c75b5
07:09
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
44f2222
07:06
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
96215bb
07:06
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
2baf059
07:04
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
5e084ea
07:04
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
dc35b21
07:02
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
fb8a64f
07:02
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
4d85c42
07:00
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
772d61e
07:00
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
bc52427
06:58
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
0488160
06:58
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
f0ffe3b
06:56
Update benchmark_suite_4k.json with latest base model evaluation scores

GiuliannoV

Verified signature
7babd12
06:56
Update README.md with latest base model evaluation scores

GiuliannoV

Verified signature
e6091af

Commit History

Oct 30 3 days ago

Link the technical report on arXiv⁠

Oct 28 5 days ago

Redraw the architecture figure as a block diagram

Oct 27 6 days ago

Redraw the architecture figure for the card width

New architecture figure and a short note

Benchmark table first

Benchmark table first; Lernex on X is @Lernex_ai

Release card and Transformers support⁠

Release under the Apache 2.0 license

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores

Update benchmark_suite_4k.json with latest base model evaluation scores

Update README.md with latest base model evaluation scores