Instructions to use rbelanec/train_cola_42_1774791067 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_cola_42_1774791067 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_cola_42_1774791067")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rbelanec/train_cola_42_1774791067")
model = AutoModelForCausalLM.from_pretrained("rbelanec/train_cola_42_1774791067")
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_cola_42_1774791067 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_cola_42_1774791067"
# 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_cola_42_1774791067",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_cola_42_1774791067

SGLang

How to use rbelanec/train_cola_42_1774791067 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_cola_42_1774791067" \
    --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_cola_42_1774791067",
		"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_cola_42_1774791067" \
        --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_cola_42_1774791067",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_cola_42_1774791067 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_cola_42_1774791067
```

train_cola_42_1774791067

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

Loss: 0.2517
Num Input Tokens Seen: 1932608

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: 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
0.2682	0.2505	241	0.3847	97664
0.3383	0.5010	482	0.4081	194560
0.2962	0.7516	723	0.2960	291712
0.2807	1.0021	964	0.2739	387464
0.2836	1.2526	1205	0.2581	485192
0.2936	1.5031	1446	0.2570	581704
0.2705	1.7536	1687	0.2560	677576
0.2243	2.0042	1928	0.2575	775312
0.2477	2.2547	2169	0.2924	873104
0.2379	2.5052	2410	0.2577	969360
0.2934	2.7557	2651	0.2561	1065232
0.2209	3.0062	2892	0.2571	1162016
0.2647	3.2568	3133	0.2563	1259168
0.2795	3.5073	3374	0.2642	1355552
0.2751	3.7578	3615	0.2587	1453088
0.279	4.0083	3856	0.2559	1549360
0.2511	4.2588	4097	0.2517	1645808
0.2709	4.5094	4338	0.2577	1742960
0.2582	4.7599	4579	0.2605	1839344

Framework versions

Transformers 4.51.3
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 3

Safetensors

Model size

1B params

Tensor type

F32

Model tree for rbelanec/train_cola_42_1774791067

Base model

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

Finetuned

(1747)

this model