Instructions to use rbelanec/train_record_42_1779354540 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_record_42_1779354540 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_record_42_1779354540")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rbelanec/train_record_42_1779354540")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_record_42_1779354540")
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 Settings

vLLM

How to use rbelanec/train_record_42_1779354540 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_record_42_1779354540"
# 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_record_42_1779354540",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_record_42_1779354540

SGLang

How to use rbelanec/train_record_42_1779354540 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_record_42_1779354540" \
    --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_record_42_1779354540",
		"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_record_42_1779354540" \
        --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_record_42_1779354540",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_record_42_1779354540 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_record_42_1779354540
```

train_record_42_1779354540

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

Loss: 0.3537
Num Input Tokens Seen: 49166912

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
0.764	0.0501	782	0.6362	2474432
0.6569	0.1001	1564	0.5395	4931328
0.5165	0.1502	2346	0.5076	7397056
0.5774	0.2002	3128	0.4884	9832064
0.4226	0.2503	3910	0.4644	12304064
0.3784	0.3004	4692	0.4629	14775488
0.579	0.3504	5474	0.4391	17259840
0.3547	0.4005	6256	0.4233	19707456
0.3794	0.4505	7038	0.4316	22178432
0.3939	0.5006	7820	0.4134	24646208
0.3382	0.5507	8602	0.3985	27101056
0.4	0.6007	9384	0.3917	29544576
0.3188	0.6508	10166	0.3784	32010176
0.4233	0.7009	10948	0.3722	34475136
0.2995	0.7509	11730	0.3648	36931648
0.3367	0.8010	12512	0.3636	39382144
0.272	0.8510	13294	0.3571	41847872
0.3451	0.9011	14076	0.3544	44318848
0.2502	0.9512	14858	0.3537	46767552

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 284

Safetensors

Model size

1B params

Tensor type

F32

BF16

Model tree for rbelanec/train_record_42_1779354540

Base model

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

Finetuned

(1749)

this model