Instructions to use hraj266/scratch_llm_results with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hraj266/scratch_llm_results with Transformers:

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

pipe = pipeline("text-generation", model="hraj266/scratch_llm_results")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hraj266/scratch_llm_results")
model = AutoModelForCausalLM.from_pretrained("hraj266/scratch_llm_results", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hraj266/scratch_llm_results with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hraj266/scratch_llm_results"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hraj266/scratch_llm_results",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hraj266/scratch_llm_results

SGLang

How to use hraj266/scratch_llm_results 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 "hraj266/scratch_llm_results" \
    --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": "hraj266/scratch_llm_results",
		"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 "hraj266/scratch_llm_results" \
        --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": "hraj266/scratch_llm_results",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hraj266/scratch_llm_results with Docker Model Runner:
```
docker model run hf.co/hraj266/scratch_llm_results
```

scratch_llm_results

This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:

Loss: 9.4696

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: 0.0005
train_batch_size: 2
eval_batch_size: 2
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
10.0792	0.5	1	9.6733
9.6563	1.0	2	9.6134
8.0019	1.5	3	9.6284
7.9470	2.0	4	9.4605
6.5463	2.5	5	9.4539
6.9528	3.0	6	9.4696

Framework versions

Transformers 5.22.0
Pytorch 2.11.0+cu130
Datasets 4.8.5
Tokenizers 0.23.3

Downloads last month: -

Safetensors

Model size

38.5M params

Tensor type

F32