Commit
•
0649f21
1
Parent(s):
2c44003
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,11 @@ tags:
|
|
| 11 |
- trl
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# Uploaded model
|
| 15 |
|
| 16 |
- **Developed by:** jjsprockel
|
|
@@ -24,7 +29,7 @@ El siguiente es el código sugerido para descargar el modelo usando Unslot:
|
|
| 24 |
import torch
|
| 25 |
from unsloth import FastLanguageModel
|
| 26 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
| 27 |
-
model_name = "jjsprockel/Patologia_lora_model1",
|
| 28 |
max_seq_length = 2048, # Choose any! Llama 3 is up to 8k
|
| 29 |
dtype = None,
|
| 30 |
load_in_4bit = True,
|
|
@@ -47,7 +52,6 @@ alpaca_prompt = """Below is an instruction that describes a task, paired with an
|
|
| 47 |
|
| 48 |
**Código para la inferencia:**
|
| 49 |
|
| 50 |
-
# Get the instruction from the console
|
| 51 |
El siguiente codigo demuestra como se puede llevar a cabo la inferencia.
|
| 52 |
|
| 53 |
```
|
|
|
|
| 11 |
- trl
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# LLM basado en LLaMA Ajustado al Dominio de Patología
|
| 15 |
+
|
| 16 |
+
Primera Versión de un LLM ajustado para responder preguntas de Patología
|
| 17 |
+
|
| 18 |
+
|
| 19 |
# Uploaded model
|
| 20 |
|
| 21 |
- **Developed by:** jjsprockel
|
|
|
|
| 29 |
import torch
|
| 30 |
from unsloth import FastLanguageModel
|
| 31 |
model, tokenizer = FastLanguageModel.from_pretrained(
|
| 32 |
+
model_name = "jjsprockel/Patologia_lora_model1",
|
| 33 |
max_seq_length = 2048, # Choose any! Llama 3 is up to 8k
|
| 34 |
dtype = None,
|
| 35 |
load_in_4bit = True,
|
|
|
|
| 52 |
|
| 53 |
**Código para la inferencia:**
|
| 54 |
|
|
|
|
| 55 |
El siguiente codigo demuestra como se puede llevar a cabo la inferencia.
|
| 56 |
|
| 57 |
```
|