Instructions to use rbelanec/train_mrpc_456_1760637795 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_mrpc_456_1760637795 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "rbelanec/train_mrpc_456_1760637795")

Transformers

How to use rbelanec/train_mrpc_456_1760637795 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_mrpc_456_1760637795")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_mrpc_456_1760637795", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_mrpc_456_1760637795 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_mrpc_456_1760637795"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rbelanec/train_mrpc_456_1760637795",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_mrpc_456_1760637795

SGLang

How to use rbelanec/train_mrpc_456_1760637795 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 "rbelanec/train_mrpc_456_1760637795" \
    --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": "rbelanec/train_mrpc_456_1760637795",
		"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 "rbelanec/train_mrpc_456_1760637795" \
        --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": "rbelanec/train_mrpc_456_1760637795",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_mrpc_456_1760637795 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_mrpc_456_1760637795
```

train_mrpc_456_1760637795

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

Loss: 0.1376
Num Input Tokens Seen: 6773216

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 456
optimizer: Use 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.2116	1.0	826	0.1892	338864
0.2104	2.0	1652	0.1653	676984
0.1469	3.0	2478	0.1562	1016176
0.2344	4.0	3304	0.1572	1354632
0.1149	5.0	4130	0.1477	1692816
0.0964	6.0	4956	0.1442	2031320
0.1655	7.0	5782	0.1421	2369768
0.1812	8.0	6608	0.1400	2708688
0.071	9.0	7434	0.1403	3047376
0.2013	10.0	8260	0.1443	3386408
0.108	11.0	9086	0.1416	3724296
0.1691	12.0	9912	0.1376	4063352
0.1233	13.0	10738	0.1437	4402032
0.0452	14.0	11564	0.1417	4740464
0.1797	15.0	12390	0.1423	5079384
0.086	16.0	13216	0.1424	5418192
0.0743	17.0	14042	0.1386	5757208
0.1652	18.0	14868	0.1406	6095648
0.1607	19.0	15694	0.1428	6434448
0.0791	20.0	16520	0.1405	6773216

Framework versions

PEFT 0.17.1
Transformers 4.51.3
Pytorch 2.9.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: -

Model tree for rbelanec/train_mrpc_456_1760637795

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Adapter

(2402)

this model