Instructions to use likkisamarth/tinyllama-log-anomaly with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use likkisamarth/tinyllama-log-anomaly with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
model = PeftModel.from_pretrained(base_model, "likkisamarth/tinyllama-log-anomaly")

Transformers

How to use likkisamarth/tinyllama-log-anomaly with Transformers:

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

pipe = pipeline("text-generation", model="likkisamarth/tinyllama-log-anomaly")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("likkisamarth/tinyllama-log-anomaly", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use likkisamarth/tinyllama-log-anomaly with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/likkisamarth/tinyllama-log-anomaly

SGLang

How to use likkisamarth/tinyllama-log-anomaly 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 "likkisamarth/tinyllama-log-anomaly" \
    --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": "likkisamarth/tinyllama-log-anomaly",
		"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 "likkisamarth/tinyllama-log-anomaly" \
        --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": "likkisamarth/tinyllama-log-anomaly",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use likkisamarth/tinyllama-log-anomaly with Docker Model Runner:
```
docker model run hf.co/likkisamarth/tinyllama-log-anomaly
```

tinyllama-log-anomaly

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0903

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: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.03
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.1011	0.1536	500	0.1007
0.0963	0.3073	1000	0.0976
0.0965	0.4609	1500	0.0953
0.0963	0.6145	2000	0.0944
0.0949	0.7682	2500	0.0936
0.0950	0.9218	3000	0.0923
0.0945	1.0753	3500	0.0914
0.0934	1.2289	4000	0.0913
0.0925	1.3825	4500	0.0908
0.0915	1.5362	5000	0.0906
0.0944	1.6898	5500	0.0904
0.0918	1.8434	6000	0.0903
0.0919	1.9971	6500	0.0903

Framework versions

PEFT 0.19.1
Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: 5

Model tree for likkisamarth/tinyllama-log-anomaly

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Adapter

(1589)

this model