Instructions to use thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22 with Transformers:

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

pipe = pipeline("text-generation", model="thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22

SGLang

How to use thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22 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 "thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22 with Docker Model Runner:
```
docker model run hf.co/thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22
```

sparse_llama_7b_refined_web_90p_2024-03-22

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.9625

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 0
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 32
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
5.3089	0.01	25	5.2010
4.692	0.02	50	4.5938
3.9452	0.02	75	3.9591
3.4555	0.03	100	3.5625
3.2557	0.04	125	3.3530
3.0322	0.05	150	3.2484
2.9015	0.06	175	3.1688
2.9955	0.06	200	3.1071

Framework versions

Transformers 4.37.2
Pytorch 2.1.1+cu121
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 3

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for thrunlab/sparse_llama_7b_refined_web_90p_2024-03-22

Base model

meta-llama/Llama-2-7b-chat-hf

Finetuned

(551)

this model