Instructions to use rbelanec/train_mrpc_42_1776331557 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_mrpc_42_1776331557 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_mrpc_42_1776331557")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rbelanec/train_mrpc_42_1776331557")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_mrpc_42_1776331557")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_mrpc_42_1776331557 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_mrpc_42_1776331557"
# 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_42_1776331557",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_mrpc_42_1776331557

SGLang

How to use rbelanec/train_mrpc_42_1776331557 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_42_1776331557" \
    --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_42_1776331557",
		"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_42_1776331557" \
        --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_42_1776331557",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_mrpc_42_1776331557 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_mrpc_42_1776331557
```

train_mrpc_42_1776331557

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the mrpc dataset. It achieves the following results on the evaluation set:

Loss: 0.1084
Num Input Tokens Seen: 1780000

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-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.1552	0.2518	104	0.1485	89600
0.2178	0.5036	208	0.1320	178688
0.1165	0.7554	312	0.1130	267968
0.1193	1.0073	416	0.1084	357488
0.0685	1.2591	520	0.1903	446896
0.0801	1.5109	624	0.1982	536176
0.2066	1.7627	728	0.1449	626992
0.0011	2.0145	832	0.2068	716344
0.0059	2.2663	936	0.2691	806712
0.0756	2.5182	1040	0.2895	895736
0.0001	2.7700	1144	0.2260	985592
0.0	3.0218	1248	0.2253	1074624
0.0	3.2736	1352	0.2578	1164544
0.0	3.5254	1456	0.2580	1253248
0.0	3.7772	1560	0.2703	1344000
0.0	4.0291	1664	0.2502	1432880
0.0001	4.2809	1768	0.2504	1522544
0.0	4.5327	1872	0.2489	1611760
0.0	4.7845	1976	0.2508	1702832

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 6

Safetensors

Model size

1B params

Tensor type

F32

Model tree for rbelanec/train_mrpc_42_1776331557

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

(1748)

this model