Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Instructions to use squareoctopus/ocampo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use squareoctopus/ocampo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="squareoctopus/ocampo")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("squareoctopus/ocampo") model = AutoModelForCausalLM.from_pretrained("squareoctopus/ocampo") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use squareoctopus/ocampo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "squareoctopus/ocampo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "squareoctopus/ocampo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/squareoctopus/ocampo
- SGLang
How to use squareoctopus/ocampo 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 "squareoctopus/ocampo" \ --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": "squareoctopus/ocampo", "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 "squareoctopus/ocampo" \ --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": "squareoctopus/ocampo", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use squareoctopus/ocampo with Docker Model Runner:
docker model run hf.co/squareoctopus/ocampo
Commit 路
f9e8790
1
Parent(s): 238fbc7
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,33 +4,42 @@ base_model: DeepESP/gpt2-spanish
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
-
- name:
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
-
|
| 12 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
|
| 14 |
-
# O
|
| 15 |
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 2.2787
|
| 19 |
|
| 20 |
-
## Model description
|
| 21 |
-
|
| 22 |
-
More information needed
|
| 23 |
|
| 24 |
## Intended uses & limitations
|
| 25 |
|
| 26 |
-
|
|
|
|
| 27 |
|
| 28 |
## Training and evaluation data
|
| 29 |
|
| 30 |
-
|
|
|
|
| 31 |
|
| 32 |
## Training procedure
|
| 33 |
|
|
|
|
|
|
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
+
- name: Ocampo
|
| 8 |
results: []
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# Silvina Ocampo - Modelo de Exploraci贸n
|
|
|
|
| 12 |
|
|
|
|
| 13 |
|
| 14 |
+
## Model description
|
| 15 |
+
|
| 16 |
+
Este modelo es una versi贸n fine-tuneada de [DeepESP/gpt2-spanish](https://huggingface.co/DeepESP/gpt2-spanish),
|
| 17 |
+
con un dataset de Autores y Autoras Latinoamericanos/as curado por Karen Palacio (https://github.com/karen-pal/borges), del cual seleccionamos a Silvina Ocampo.
|
| 18 |
+
Fue creado durante un taller enfocado en exploraci贸n de LLMs por miembros de LAIA (laia.ar), siguiendo en grupo el Taller de Adaptaci贸n de Modelos de Lenguaje de Fundaci贸n Via Libre (https://github.com/nanom/llm_adaptation_workshop)
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [DeepESP/gpt2-spanish](https://huggingface.co/DeepESP/gpt2-spanish),
|
| 21 |
+
with a dataset of Latin American authors by Karen Palacio (https://github.com/karen-pal/borges), of which Silvina Ocampo's work was chosen.
|
| 22 |
+
It was created during a workshop focused on LLM exploration by members of LAIA (laia.ar), by group-following the LLM Adaptation Workshop by Fundaci贸n Via Libre (https://github.com/nanom/llm_adaptation_workshop)
|
| 23 |
+
|
| 24 |
It achieves the following results on the evaluation set:
|
| 25 |
- Loss: 2.2787
|
| 26 |
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
## Intended uses & limitations
|
| 29 |
|
| 30 |
+
El modelo fue fine-tuneado como ejercicio educativo.
|
| 31 |
+
This model was fine tuned as an educational exercise.
|
| 32 |
|
| 33 |
## Training and evaluation data
|
| 34 |
|
| 35 |
+
- ver https://github.com/karen-pal/borges para los datasets. En este ejercicio, tambi茅n agregamos un cuento no disponible en los datos originales.
|
| 36 |
+
- see the link above for the datasets
|
| 37 |
|
| 38 |
## Training procedure
|
| 39 |
|
| 40 |
+
- ver https://github.com/nanom/llm_adaptation_workshop para el procedimiento de entrenamiento.
|
| 41 |
+
- see the link above for the training procedure.
|
| 42 |
+
|
| 43 |
### Training hyperparameters
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|