Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/llama-3.2-1b-instruct-bnb-4bit
|
| 3 |
language:
|
| 4 |
-
-
|
| 5 |
license: apache-2.0
|
| 6 |
tags:
|
| 7 |
- text-generation-inference
|
|
@@ -9,8 +9,35 @@ tags:
|
|
| 9 |
- unsloth
|
| 10 |
- llama
|
| 11 |
- gguf
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# Uploaded model
|
| 15 |
|
| 16 |
- **Developed by:** ussipan
|
|
@@ -20,3 +47,12 @@ tags:
|
|
| 20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 21 |
|
| 22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/llama-3.2-1b-instruct-bnb-4bit
|
| 3 |
language:
|
| 4 |
+
- es
|
| 5 |
license: apache-2.0
|
| 6 |
tags:
|
| 7 |
- text-generation-inference
|
|
|
|
| 9 |
- unsloth
|
| 10 |
- llama
|
| 11 |
- gguf
|
| 12 |
+
- q4_k_m
|
| 13 |
+
- 4bit
|
| 14 |
+
- sharegpt
|
| 15 |
+
- pretaining
|
| 16 |
+
- finetuning
|
| 17 |
+
- Q5_K_M
|
| 18 |
+
- Q8_0
|
| 19 |
+
- uss
|
| 20 |
+
- Perú
|
| 21 |
+
- Lambayeque
|
| 22 |
+
- Chiclayo
|
| 23 |
+
datasets:
|
| 24 |
+
- ussipan/sipangpt
|
| 25 |
+
new_version: ussipan/SipanGPT-0.2-Llama-3.2-1B-GGUF
|
| 26 |
+
pipeline_tag: text2text-generation
|
| 27 |
---
|
| 28 |
|
| 29 |
+
# SipánGPT 0.3 Llama 3.2 1B GGUF
|
| 30 |
+
- Modelo pre-entrenado para responder preguntas de la Universidad Señor de Sipán de Lambayeque, Perú.
|
| 31 |
+
- Pre-trained model to answer questions from the Señor de Sipán University of Lambayeque, Peru.
|
| 32 |
+
|
| 33 |
+
## Testing the model
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
- Entrenado con 50000 conversaciones, el modelo puede generar alucinaciones.
|
| 39 |
+
- Trained with 50000 conversations, the model can generate hallucinations
|
| 40 |
+
|
| 41 |
# Uploaded model
|
| 42 |
|
| 43 |
- **Developed by:** ussipan
|
|
|
|
| 47 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 48 |
|
| 49 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
| 50 |
+
|
| 51 |
+
---
|
| 52 |
+
|
| 53 |
+
## SipánGPT 0.3 Llama 3.2 1B GGUF
|
| 54 |
+
|
| 55 |
+
<div style="display: flex; align-items: center; height: fit-content;">
|
| 56 |
+
<img src="https://avatars.githubusercontent.com/u/60937214?v=4" width="40" style="margin-right: 10px;"/>
|
| 57 |
+
<span>Hecho con ❤️ por Jhan Gómez P.</span>
|
| 58 |
+
</div>
|