Instructions to use ZigZeug/logllm-llama3-8b-BGL-logs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZigZeug/logllm-llama3-8b-BGL-logs with Transformers:

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

pipe = pipeline("text-generation", model="ZigZeug/logllm-llama3-8b-BGL-logs", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZigZeug/logllm-llama3-8b-BGL-logs")
model = AutoModelForCausalLM.from_pretrained("ZigZeug/logllm-llama3-8b-BGL-logs", device_map="auto")

PEFT
How to use ZigZeug/logllm-llama3-8b-BGL-logs with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZigZeug/logllm-llama3-8b-BGL-logs with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZigZeug/logllm-llama3-8b-BGL-logs"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZigZeug/logllm-llama3-8b-BGL-logs",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ZigZeug/logllm-llama3-8b-BGL-logs

SGLang

How to use ZigZeug/logllm-llama3-8b-BGL-logs 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 "ZigZeug/logllm-llama3-8b-BGL-logs" \
    --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": "ZigZeug/logllm-llama3-8b-BGL-logs",
		"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 "ZigZeug/logllm-llama3-8b-BGL-logs" \
        --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": "ZigZeug/logllm-llama3-8b-BGL-logs",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ZigZeug/logllm-llama3-8b-BGL-logs with Docker Model Runner:
```
docker model run hf.co/ZigZeug/logllm-llama3-8b-BGL-logs
```

LogLLM - Llama 3 8B Fine-tuned for Log Analysis

Ce modèle est une version fine-tunée de Llama 3 8B spécialisée dans l'analyse de logs système.

Utilisation

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

# Chargement du modèle
tokenizer = AutoTokenizer.from_pretrained("ZigZeug/logllm-llama3-8b-BGL-logs")
model = AutoModelForCausalLM.from_pretrained("ZigZeug/logllm-llama3-8b-BGL-logs")

# Création du pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

Entraînement

Ce modèle a été fine-tuné sur des datasets de logs système pour améliorer ses capacités d'analyse et de diagnostic.

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

F16

Model tree for ZigZeug/logllm-llama3-8b-BGL-logs

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

(607)

this model