Instructions to use walid-iguider/Llama-3-8B-4bit-UltraChat-Ita with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use walid-iguider/Llama-3-8B-4bit-UltraChat-Ita with Transformers:

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

pipe = pipeline("text-generation", model="walid-iguider/Llama-3-8B-4bit-UltraChat-Ita")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("walid-iguider/Llama-3-8B-4bit-UltraChat-Ita")
model = AutoModelForCausalLM.from_pretrained("walid-iguider/Llama-3-8B-4bit-UltraChat-Ita", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use walid-iguider/Llama-3-8B-4bit-UltraChat-Ita with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "walid-iguider/Llama-3-8B-4bit-UltraChat-Ita"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "walid-iguider/Llama-3-8B-4bit-UltraChat-Ita",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/walid-iguider/Llama-3-8B-4bit-UltraChat-Ita

SGLang

How to use walid-iguider/Llama-3-8B-4bit-UltraChat-Ita 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 "walid-iguider/Llama-3-8B-4bit-UltraChat-Ita" \
    --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": "walid-iguider/Llama-3-8B-4bit-UltraChat-Ita",
		"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 "walid-iguider/Llama-3-8B-4bit-UltraChat-Ita" \
        --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": "walid-iguider/Llama-3-8B-4bit-UltraChat-Ita",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use walid-iguider/Llama-3-8B-4bit-UltraChat-Ita with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for walid-iguider/Llama-3-8B-4bit-UltraChat-Ita to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for walid-iguider/Llama-3-8B-4bit-UltraChat-Ita to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for walid-iguider/Llama-3-8B-4bit-UltraChat-Ita to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="walid-iguider/Llama-3-8B-4bit-UltraChat-Ita",
    max_seq_length=2048,
)

Docker Model Runner
How to use walid-iguider/Llama-3-8B-4bit-UltraChat-Ita with Docker Model Runner:
```
docker model run hf.co/walid-iguider/Llama-3-8B-4bit-UltraChat-Ita
```

walid-iguider

FinancialSupport commited on May 6, 2024

Commit

473a2ee

verified ·

1 Parent(s): 60dde8d

Update README.md (#1)

Browse files

- Update README.md (8af75876bfdfc33c4f81882cdd7d464018154f2c)

Co-authored-by: Samuele Colombo <FinancialSupport@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +10 -0

README.md CHANGED Viewed

@@ -12,6 +12,9 @@ tags:
 base_model: unsloth/llama-3-8b-bnb-4bit
 datasets:
 - mii-community/ultrafeedback-translated-ita
 ---
 # Uploaded  model
@@ -22,4 +25,11 @@ datasets:
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 base_model: unsloth/llama-3-8b-bnb-4bit
 datasets:
 - mii-community/ultrafeedback-translated-ita
+## Evaluation
 ---
 # Uploaded  model
 This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+For a detailed comparison of model performance, check out the [Leaderboard for Italian Language Models](https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard).
+Here's a breakdown of the performance metrics:
+| Metric                      | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
+|:----------------------------|:----------------------|:----------------|:---------------------|:--------|
+| **Accuracy Normalized**     | 0.6064                | 0.4611        | 0.5328                 | 0.5334  |
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)