Instructions to use utter-project/EuroLLM1.5-9B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use utter-project/EuroLLM1.5-9B-Base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="utter-project/EuroLLM1.5-9B-Base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("utter-project/EuroLLM1.5-9B-Base") model = AutoModelForCausalLM.from_pretrained("utter-project/EuroLLM1.5-9B-Base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use utter-project/EuroLLM1.5-9B-Base with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "utter-project/EuroLLM1.5-9B-Base" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "utter-project/EuroLLM1.5-9B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/utter-project/EuroLLM1.5-9B-Base
- SGLang
How to use utter-project/EuroLLM1.5-9B-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 "utter-project/EuroLLM1.5-9B-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": "utter-project/EuroLLM1.5-9B-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 "utter-project/EuroLLM1.5-9B-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": "utter-project/EuroLLM1.5-9B-Base", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use utter-project/EuroLLM1.5-9B-Base with Docker Model Runner:
docker model run hf.co/utter-project/EuroLLM1.5-9B-Base
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,9 @@ library_name: transformers
|
|
| 41 |
|
| 42 |
## Results
|
| 43 |
|
| 44 |
-
|
|
|
|
|
|
|
| 45 |
|
| 46 |
<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0;overflow-x:auto">
|
| 47 |
<table style="width:648px;min-width:648px;table-layout:fixed;border-collapse:collapse;font-size:13px">
|
|
@@ -50,8 +52,8 @@ We compare EuroLLM1.5-9B-Base against the previous EuroLLM base releases (EuroLL
|
|
| 50 |
<th style="width:120px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap;background:rgba(37, 99, 235, 0.06);font-weight:700">EuroLLM1.5-9B-Base</th>
|
| 51 |
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">EuroLLM-9B-2512</th>
|
| 52 |
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">EuroLLM-22B-2512</th>
|
| 53 |
-
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">Apertus-v1.5-8B</th>
|
| 54 |
-
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">Prelude 9B</th>
|
| 55 |
</tr></thead>
|
| 56 |
<tbody>
|
| 57 |
<tr><td colspan="6" style="padding:9px 12px;font-weight:700;color:#ffffff;background:#2563eb;letter-spacing:0.5px">English</td></tr>
|
|
|
|
| 41 |
|
| 42 |
## Results
|
| 43 |
|
| 44 |
+
**Note:** The evaluation results presented below are preliminary and subject to further verification. Final results, together with detailed evaluation configurations and methodology to ensure reproducibility, will be made available soon.
|
| 45 |
+
|
| 46 |
+
We compare EuroLLM1.5-9B-Base against the previous EuroLLM base releases (EuroLLM-9B-2512 and EuroLLM-22B-2512) and two European open base models of similar size, Apertus-v1.5-8B and OpenEuroLLM Prelude 9B, on English and multilingual benchmarks covering math, reasoning, coding, knowledge and reading comprehension.
|
| 47 |
|
| 48 |
<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:1000px;margin:0 auto;padding:16px 0;overflow-x:auto">
|
| 49 |
<table style="width:648px;min-width:648px;table-layout:fixed;border-collapse:collapse;font-size:13px">
|
|
|
|
| 52 |
<th style="width:120px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap;background:rgba(37, 99, 235, 0.06);font-weight:700">EuroLLM1.5-9B-Base</th>
|
| 53 |
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">EuroLLM-9B-2512</th>
|
| 54 |
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">EuroLLM-22B-2512</th>
|
| 55 |
+
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">Apertus-v1.5-8B-base</th>
|
| 56 |
+
<th style="width:108px;padding:10px 5px;text-align:center;font-weight:500;border-bottom:2px solid #2563eb;color:#2563eb;font-size:12px;white-space:nowrap">OpenEuroLLM Prelude-base 9B</th>
|
| 57 |
</tr></thead>
|
| 58 |
<tbody>
|
| 59 |
<tr><td colspan="6" style="padding:9px 12px;font-weight:700;color:#ffffff;background:#2563eb;letter-spacing:0.5px">English</td></tr>
|