Instructions to use rbelanec/train_cb_42_1760637523 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rbelanec/train_cb_42_1760637523 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_42_1760637523")

Transformers

How to use rbelanec/train_cb_42_1760637523 with Transformers:

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

pipe = pipeline("text-generation", model="rbelanec/train_cb_42_1760637523")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rbelanec/train_cb_42_1760637523", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rbelanec/train_cb_42_1760637523 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rbelanec/train_cb_42_1760637523"
# 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_42_1760637523",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rbelanec/train_cb_42_1760637523

SGLang

How to use rbelanec/train_cb_42_1760637523 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_42_1760637523" \
    --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_42_1760637523",
		"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_42_1760637523" \
        --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_42_1760637523",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rbelanec/train_cb_42_1760637523 with Docker Model Runner:
```
docker model run hf.co/rbelanec/train_cb_42_1760637523
```

train_cb_42_1760637523

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: 0.1325
Num Input Tokens Seen: 725992

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: 0.03
train_batch_size: 4
eval_batch_size: 4
seed: 42
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
0.6057	1.0	57	1.3882	36480
0.3279	2.0	114	0.3234	72112
0.2478	3.0	171	0.2578	108712
0.1393	4.0	228	0.2197	145296
0.2443	5.0	285	0.1910	181408
0.1904	6.0	342	0.2125	217760
0.092	7.0	399	0.1999	254568
0.285	8.0	456	0.1869	291000
0.1165	9.0	513	0.2022	327792
0.1643	10.0	570	0.2083	363864
0.1546	11.0	627	0.1881	400104
0.3025	12.0	684	0.1756	436440
0.1343	13.0	741	0.1456	471944
0.1078	14.0	798	0.2014	508424
0.2187	15.0	855	0.1325	545352
0.0431	16.0	912	0.1589	581368
0.0308	17.0	969	0.1602	616776
0.0234	18.0	1026	0.1673	653152
0.0289	19.0	1083	0.1704	689856
0.0121	20.0	1140	0.1693	725992

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_42_1760637523

Base model

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

Adapter

(2405)

this model