Instructions to use Harshatheeswar/babylama-hidden_layers12 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Harshatheeswar/babylama-hidden_layers12 with Transformers:

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

pipe = pipeline("text-generation", model="Harshatheeswar/babylama-hidden_layers12")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Harshatheeswar/babylama-hidden_layers12")
model = AutoModelForMultimodalLM.from_pretrained("Harshatheeswar/babylama-hidden_layers12")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Harshatheeswar/babylama-hidden_layers12 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harshatheeswar/babylama-hidden_layers12"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Harshatheeswar/babylama-hidden_layers12",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Harshatheeswar/babylama-hidden_layers12

SGLang

How to use Harshatheeswar/babylama-hidden_layers12 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 "Harshatheeswar/babylama-hidden_layers12" \
    --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": "Harshatheeswar/babylama-hidden_layers12",
		"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 "Harshatheeswar/babylama-hidden_layers12" \
        --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": "Harshatheeswar/babylama-hidden_layers12",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Harshatheeswar/babylama-hidden_layers12 with Docker Model Runner:
```
docker model run hf.co/Harshatheeswar/babylama-hidden_layers12
```

Harshatheeswar commited on Nov 13, 2024

Commit

a3d1708

verified ·

1 Parent(s): 8ff647b

End of training

Browse files

Files changed (3) hide show

README.md +64 -0
generation_config.json +7 -0
runs/Nov13_09-10-54_5b91a2bf3201/events.out.tfevents.1731489057.5b91a2bf3201.1016.0 +2 -2

README.md ADDED Viewed

	@@ -0,0 +1,64 @@

+---
+library_name: transformers
+base_model: Harshatheeswar/babylama-hidden_sizes768
+tags:
+- generated_from_trainer
+model-index:
+- name: babylama-hidden_layers12
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# babylama-hidden_layers12
+This model is a fine-tuned version of [Harshatheeswar/babylama-hidden_sizes768](https://huggingface.co/Harshatheeswar/babylama-hidden_sizes768) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8091
+## 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
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- 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
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+### Training results
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 4.1221        | 0.9999 | 5559  | 4.1310          |
+| 3.776         | 1.9999 | 11119 | 3.8951          |
+| 3.5749        | 2.9998 | 16678 | 3.8044          |
+| 3.4408        | 3.9999 | 22238 | 3.7917          |
+| 3.3023        | 4.9994 | 27795 | 3.8091          |
+### Framework versions
+- Transformers 4.46.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

generation_config.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.2"
+}

runs/Nov13_09-10-54_5b91a2bf3201/events.out.tfevents.1731489057.5b91a2bf3201.1016.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b77ceb63eeec6eb2c37971752554bdd3a15c3b1a3247c2d50862e2bfb9dea67
-size 597157

 version https://git-lfs.github.com/spec/v1
+oid sha256:1e7eec8fcc242c6cdd8f8a5b261397c437e67c61ddf4d2c4e27bf15bb2426533
+size 597793