Instructions to use l3utterfly/llama2-7b-layla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use l3utterfly/llama2-7b-layla with Transformers:

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

pipe = pipeline("text-generation", model="l3utterfly/llama2-7b-layla")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("l3utterfly/llama2-7b-layla")
model = AutoModelForCausalLM.from_pretrained("l3utterfly/llama2-7b-layla")

Inference
Local Apps Settings

vLLM

How to use l3utterfly/llama2-7b-layla with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "l3utterfly/llama2-7b-layla"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "l3utterfly/llama2-7b-layla",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/l3utterfly/llama2-7b-layla

SGLang

How to use l3utterfly/llama2-7b-layla 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 "l3utterfly/llama2-7b-layla" \
    --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": "l3utterfly/llama2-7b-layla",
		"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 "l3utterfly/llama2-7b-layla" \
        --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": "l3utterfly/llama2-7b-layla",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use l3utterfly/llama2-7b-layla with Docker Model Runner:
```
docker model run hf.co/l3utterfly/llama2-7b-layla
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card

Model Description

Llama2 7B fine-tuned using ShareGPT datasets for multi-turn conversations.

Developed by: l3utterfly
Funded by: Layla Network
Model type: Llama2
Language(s) (NLP): English
License: Llama2
Finetuned from model: Llama2 7B

Uses

Base model used by Layla - the offline personal assistant: https://www.layla-network.ai

Help & support: https://discord.gg/x546YJ6nYC

Prompt:

User:
Assistant:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	45.56
ARC (25-shot)	54.18
HellaSwag (10-shot)	79.34
MMLU (5-shot)	49.7
TruthfulQA (0-shot)	46.5
Winogrande (5-shot)	74.11
GSM8K (5-shot)	8.49
DROP (3-shot)	6.57

Downloads last month: 218

Model tree for l3utterfly/llama2-7b-layla

Quantizations

3 models

l3utterfly
/

llama2-7b-layla

Model Card

Model Description

Uses

Open LLM Leaderboard Evaluation Results

Model tree for l3utterfly/llama2-7b-layla

Spaces using l3utterfly/llama2-7b-layla 29