Instructions to use rbelanec/train_mnli_42_1779286677 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_mnli_42_1779286677 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_mnli_42_1779286677")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rbelanec/train_mnli_42_1779286677")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_mnli_42_1779286677")
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_mnli_42_1779286677 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_mnli_42_1779286677"
# 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_mnli_42_1779286677",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_mnli_42_1779286677

SGLang

How to use rbelanec/train_mnli_42_1779286677 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_mnli_42_1779286677" \
    --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_mnli_42_1779286677",
		"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_mnli_42_1779286677" \
        --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_mnli_42_1779286677",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_mnli_42_1779286677 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_mnli_42_1779286677
```

train_mnli_42_1779286677

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

Loss: 0.1007
Num Input Tokens Seen: 38288928

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: 2e-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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.1805	0.0500	2209	0.1564	1902848
0.1328	0.1000	4418	0.1287	3830208
0.1111	0.1500	6627	0.1695	5746816
0.0485	0.2000	8836	0.1159	7653120
0.1612	0.2500	11045	0.1187	9565376
0.0932	0.3000	13254	0.1261	11476480
0.0607	0.3500	15463	0.1186	13403072
0.065	0.4000	17672	0.1276	15322176
0.1503	0.4500	19881	0.1237	17253696
0.0817	0.5000	22090	0.1152	19168640
0.1078	0.5500	24299	0.1187	21061760
0.094	0.6000	26508	0.1096	22967296
0.1425	0.6500	28717	0.1052	24888448
0.0465	0.7000	30926	0.1023	26807552
0.1499	0.7500	33135	0.1029	28714304
0.1164	0.8000	35344	0.1083	30627136
0.0674	0.8500	37553	0.1007	32537600
0.0278	0.9000	39762	0.1026	34457664
0.0646	0.9500	41971	0.1025	36377344

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 262

Safetensors

Model size

1B params

Tensor type

F32

BF16

Model tree for rbelanec/train_mnli_42_1779286677

Base model

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

Finetuned

(1748)

this model