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

Libraries

How to use hlillemark/combined_sft_mc_filtered with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hlillemark/combined_sft_mc_filtered")
model = AutoModelForCausalLM.from_pretrained("hlillemark/combined_sft_mc_filtered", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hlillemark/combined_sft_mc_filtered with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hlillemark/combined_sft_mc_filtered

SGLang

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

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

combined_sft_mc_filtered / README.md

hlillemark

Update README.md

3f7c4a2 verified over 1 year ago

preview code

Raw History Blame Contribute Delete

2.35 kB

metadata

library_name: transformers
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: combined_sft_mc_filtered
    results: []
datasets:
  - hlillemark/mc_combined_sa_ma_dataset

combined_sft_mc_filtered

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the identity and the data_mc_filtered datasets. It achieves the following results on the evaluation set:

Loss: 1.2652

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: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 16
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.7445	0.7463	50	0.7196
0.576	1.4925	100	0.7831
0.3113	2.2388	150	0.8755
0.3723	2.9851	200	0.8511
0.2325	3.7313	250	0.8775
0.1831	4.4776	300	0.9325
0.107	5.2239	350	1.0493
0.0884	5.9701	400	0.9148
0.0442	6.7164	450	1.0387
0.0367	7.4627	500	1.1612
0.0111	8.2090	550	1.1844
0.016	8.9552	600	1.2519
0.0057	9.7015	650	1.2654

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0