Instructions to use SemanticAlignment/Llama-3.1-8B-Italian-FVT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SemanticAlignment/Llama-3.1-8B-Italian-FVT with Transformers:

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

pipe = pipeline("text-generation", model="SemanticAlignment/Llama-3.1-8B-Italian-FVT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SemanticAlignment/Llama-3.1-8B-Italian-FVT")
model = AutoModelForCausalLM.from_pretrained("SemanticAlignment/Llama-3.1-8B-Italian-FVT")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SemanticAlignment/Llama-3.1-8B-Italian-FVT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SemanticAlignment/Llama-3.1-8B-Italian-FVT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SemanticAlignment/Llama-3.1-8B-Italian-FVT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SemanticAlignment/Llama-3.1-8B-Italian-FVT

SGLang

How to use SemanticAlignment/Llama-3.1-8B-Italian-FVT 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 "SemanticAlignment/Llama-3.1-8B-Italian-FVT" \
    --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": "SemanticAlignment/Llama-3.1-8B-Italian-FVT",
		"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 "SemanticAlignment/Llama-3.1-8B-Italian-FVT" \
        --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": "SemanticAlignment/Llama-3.1-8B-Italian-FVT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SemanticAlignment/Llama-3.1-8B-Italian-FVT with Docker Model Runner:
```
docker model run hf.co/SemanticAlignment/Llama-3.1-8B-Italian-FVT
```

Add library_name and pipeline_tag to metadata

by nielsr HF Staff - opened Apr 29, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-6

Files changed (1) hide show

README.md +8 -6

README.md CHANGED Viewed

@@ -1,8 +1,10 @@
 ---
-license: apache-2.0
 language:
 - it
 - en
 ---
 # Llama-3.1-8B-Italian-FVT
@@ -14,9 +16,9 @@ language:
 The **Llama-3.1-8B-Adapted** collection of large language models (LLMs), is a collection of adapted generative models in 8B (text in/text out), adapted models from **Llama-3.1-8B**.
-*Llama-3.1-8B-Italian-FVT* is a continual trained mistral model, after tokenizer substitution.
-The tokenizer of this models after adaptation is the same of [Minverva-3B](https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0).
 **Model developer:** SapienzaNLP, ISTI-CNR, ILC-CNR
@@ -24,15 +26,15 @@ The tokenizer of this models after adaptation is the same of [Minverva-3B](https
 ## Data used for the adaptation
-The **Mistral-7B-v0.1-Adapted** model are trained on a collection of Italian and English data extracted from [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX).
-The data are extracted to be skewed toward Italian language with a ration of one over four. Extracting the first 9B tokens from Italian part of CulturaX and the first 3B tokens from English part of CulturaX.
 ## Use with Transformers
 You can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.
-Make sure to update your transformers installation via pip install --upgrade transformers.
 ```python
 import transformers

 ---
 language:
 - it
 - en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
 # Llama-3.1-8B-Italian-FVT
 The **Llama-3.1-8B-Adapted** collection of large language models (LLMs), is a collection of adapted generative models in 8B (text in/text out), adapted models from **Llama-3.1-8B**.
+*Llama-3.1-8B-Italian-FVT* is a continually trained Mistral model, after tokenizer substitution.
+The tokenizer of this model after adaptation is the same as [Minverva-3B](https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0).
 **Model developer:** SapienzaNLP, ISTI-CNR, ILC-CNR
 ## Data used for the adaptation
+The **Mistral-7B-v0.1-Adapted** model was trained on a collection of Italian and English data extracted from [CulturaX](https://huggingface.co/datasets/uonlp/CulturaX).
+The data was extracted to be skewed toward Italian language with a ratio of one over four. Extracting the first 9B tokens from the Italian part of CulturaX and the first 3B tokens from the English part of CulturaX.
 ## Use with Transformers
 You can run conversational inference using the Transformers pipeline abstraction or by leveraging the Auto classes with the generate() function.
+Make sure to update your transformers installation via `pip install --upgrade transformers`.
 ```python
 import transformers