Instructions to use Codemaster67/OLmo-chebl_domain_adaption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Codemaster67/OLmo-chebl_domain_adaption with Transformers:

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

pipe = pipeline("text-generation", model="Codemaster67/OLmo-chebl_domain_adaption")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Codemaster67/OLmo-chebl_domain_adaption")
model = AutoModelForMultimodalLM.from_pretrained("Codemaster67/OLmo-chebl_domain_adaption")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Codemaster67/OLmo-chebl_domain_adaption with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Codemaster67/OLmo-chebl_domain_adaption"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Codemaster67/OLmo-chebl_domain_adaption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Codemaster67/OLmo-chebl_domain_adaption

SGLang

How to use Codemaster67/OLmo-chebl_domain_adaption 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 "Codemaster67/OLmo-chebl_domain_adaption" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Codemaster67/OLmo-chebl_domain_adaption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Codemaster67/OLmo-chebl_domain_adaption" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Codemaster67/OLmo-chebl_domain_adaption",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Codemaster67/OLmo-chebl_domain_adaption with Docker Model Runner:
```
docker model run hf.co/Codemaster67/OLmo-chebl_domain_adaption
```

OLmo-chebl_domain_adaption

This model is a fine-tuned version of allenai/OLMo-7B-hf on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3516
Model Preparation Time: 0.0043

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: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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_steps: 0.05
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time
6.3473	0.0710	50	6.2448	0.0043
4.8393	0.1419	100	4.6801	0.0043
3.2501	0.2129	150	3.2598	0.0043
2.7432	0.2839	200	2.8011	0.0043
2.4688	0.3549	250	2.4233	0.0043
2.2724	0.4258	300	2.2580	0.0043
2.1390	0.4968	350	2.1196	0.0043
1.9718	0.5678	400	2.0202	0.0043
1.8871	0.6388	450	1.9191	0.0043
1.8967	0.7097	500	1.8318	0.0043
1.7147	0.7807	550	1.7578	0.0043
1.7526	0.8517	600	1.7118	0.0043
1.6391	0.9226	650	1.6556	0.0043
1.5693	0.9936	700	1.6024	0.0043
1.4872	1.0639	750	1.5712	0.0043
1.4543	1.1348	800	1.5263	0.0043
1.4862	1.2058	850	1.4896	0.0043
1.3994	1.2768	900	1.4550	0.0043
1.2903	1.3478	950	1.4253	0.0043
1.2909	1.4187	1000	1.4001	0.0043
1.2847	1.4897	1050	1.3812	0.0043
1.2536	1.5607	1100	1.3681	0.0043
1.2414	1.6317	1150	1.3592	0.0043
1.3003	1.7026	1200	1.3541	0.0043
1.3042	1.7736	1250	1.3523	0.0043
1.3176	1.8446	1300	1.3517	0.0043
1.2306	1.9155	1350	1.3516	0.0043
1.2716	1.9865	1400	1.3515	0.0043
1.3064	2.0	1410	1.3516	0.0043

Framework versions

Transformers 5.9.0
Pytorch 2.8.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: 113

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Codemaster67/OLmo-chebl_domain_adaption

Base model

allenai/OLMo-7B-hf

Finetuned

(9)

this model