Instructions to use rtferraz/ecommerce-domain-24m-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rtferraz/ecommerce-domain-24m-v2 with Transformers:

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

pipe = pipeline("text-generation", model="rtferraz/ecommerce-domain-24m-v2", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("rtferraz/ecommerce-domain-24m-v2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rtferraz/ecommerce-domain-24m-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rtferraz/ecommerce-domain-24m-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rtferraz/ecommerce-domain-24m-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rtferraz/ecommerce-domain-24m-v2

SGLang

How to use rtferraz/ecommerce-domain-24m-v2 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 "rtferraz/ecommerce-domain-24m-v2" \
    --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": "rtferraz/ecommerce-domain-24m-v2",
		"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 "rtferraz/ecommerce-domain-24m-v2" \
        --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": "rtferraz/ecommerce-domain-24m-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rtferraz/ecommerce-domain-24m-v2 with Docker Model Runner:
```
docker model run hf.co/rtferraz/ecommerce-domain-24m-v2
```

rtferraz commited on 19 days ago

Commit

53d0414

verified ·

1 Parent(s): f25be3a

End of training

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -3,14 +3,14 @@ library_name: transformers
 tags:
 - generated_from_trainer
 model-index:
-- name: ecommerce-domain-24m
   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. -->
-# ecommerce-domain-24m
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
@@ -39,8 +39,8 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - optimizer: Use adamw_torch_fused 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: 200
-- num_epochs: 3
 ### Training results

 tags:
 - generated_from_trainer
 model-index:
+- name: ecommerce-domain-24m-v2
   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. -->
+# ecommerce-domain-24m-v2
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 - total_train_batch_size: 128
 - optimizer: Use adamw_torch_fused 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: 500
+- num_epochs: 10
 ### Training results