Instructions to use rbelanec/train_cb_123_1760637641 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_cb_123_1760637641 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_cb_123_1760637641")

Transformers

How to use rbelanec/train_cb_123_1760637641 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_cb_123_1760637641")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_cb_123_1760637641", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_cb_123_1760637641 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_cb_123_1760637641"
# 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_cb_123_1760637641",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_cb_123_1760637641

SGLang

How to use rbelanec/train_cb_123_1760637641 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_cb_123_1760637641" \
    --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_cb_123_1760637641",
		"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_cb_123_1760637641" \
        --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_cb_123_1760637641",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_cb_123_1760637641 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_cb_123_1760637641
```

train_cb_123_1760637641

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

Loss: 0.9343
Num Input Tokens Seen: 742296

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: 123
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
1.1045	1.0	57	1.0770	37160
1.0563	2.0	114	1.0650	73720
1.2181	3.0	171	1.0362	110296
0.9715	4.0	228	1.0253	147784
0.9201	5.0	285	0.9905	184368
0.858	6.0	342	0.9656	221536
0.973	7.0	399	0.9565	258720
1.0439	8.0	456	0.9543	295408
1.0283	9.0	513	0.9408	332648
1.1097	10.0	570	0.9428	369976
0.8619	11.0	627	0.9417	406840
0.9263	12.0	684	0.9387	444728
1.0058	13.0	741	0.9346	481720
1.0511	14.0	798	0.9343	518664
0.9927	15.0	855	0.9363	555728
0.8666	16.0	912	0.9389	593096
0.7855	17.0	969	0.9405	629760
0.8856	18.0	1026	0.9403	667432
0.9045	19.0	1083	0.9556	704816
0.7929	20.0	1140	0.9411	742296

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_cb_123_1760637641

Base model

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

Adapter

(2403)

this model