Instructions to use rbelanec/train_copa_123_1760637649 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_copa_123_1760637649 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_copa_123_1760637649")

Transformers

How to use rbelanec/train_copa_123_1760637649 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_copa_123_1760637649")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_copa_123_1760637649", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_copa_123_1760637649 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_copa_123_1760637649"
# 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_copa_123_1760637649",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_copa_123_1760637649

SGLang

How to use rbelanec/train_copa_123_1760637649 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_copa_123_1760637649" \
    --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_copa_123_1760637649",
		"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_copa_123_1760637649" \
        --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_copa_123_1760637649",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_copa_123_1760637649 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_copa_123_1760637649
```

train_copa_123_1760637649

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

Loss: 0.1102
Num Input Tokens Seen: 563328

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
0.7625	1.0	90	0.6500	28096
0.0975	2.0	180	0.1431	56128
0.0571	3.0	270	0.1310	84352
0.0225	4.0	360	0.1246	112576
0.0204	5.0	450	0.1229	140832
0.0187	6.0	540	0.1185	169056
0.0748	7.0	630	0.1122	197344
0.0294	8.0	720	0.1161	225536
0.0369	9.0	810	0.1143	253696
0.0663	10.0	900	0.1121	281856
0.0895	11.0	990	0.1120	310080
0.1041	12.0	1080	0.1129	338144
0.1611	13.0	1170	0.1122	366336
0.0268	14.0	1260	0.1117	394464
0.0043	15.0	1350	0.1117	422592
0.004	16.0	1440	0.1119	450624
0.0254	17.0	1530	0.1102	478720
0.0157	18.0	1620	0.1130	507008
0.0159	19.0	1710	0.1129	535136
0.0517	20.0	1800	0.1133	563328

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_copa_123_1760637649

Base model

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

Adapter

(2403)

this model