Update README.md
Browse files
README.md
CHANGED
@@ -11,8 +11,8 @@ widget:
|
|
11 |
content: What is your favorite condiment?
|
12 |
---
|
13 |
|
14 |
-
# versae/filiberto-7B-instruct
|
15 |
-
This model was converted to MLX format from [`mistralai/Mistral-7B-Instruct-v0.2`]() using mlx-lm version **0.9.0**.
|
16 |
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) for more details on the model.
|
17 |
## Use with mlx
|
18 |
|
@@ -23,6 +23,21 @@ pip install mlx-lm
|
|
23 |
```python
|
24 |
from mlx_lm import load, generate
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
model, tokenizer = load("versae/filiberto-7B-instruct")
|
27 |
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
28 |
```
|
|
|
11 |
content: What is your favorite condiment?
|
12 |
---
|
13 |
|
14 |
+
# versae/filiberto-7B-instruct-exp1
|
15 |
+
This model was converted to MLX format from [`mistralai/Mistral-7B-Instruct-v0.2`](https://hf.co/mistralai/Mistral-7B-Instruct-v0.2) using mlx-lm version **0.9.0**.
|
16 |
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) for more details on the model.
|
17 |
## Use with mlx
|
18 |
|
|
|
23 |
```python
|
24 |
from mlx_lm import load, generate
|
25 |
|
26 |
+
prompt = """<s>[INST] Dado el siguiente texto OCR, corrige los fallos que encuentres y devuelve el texto corregido:
|
27 |
+
|
28 |
+
Otra vez, Don Iuan, me dad,
|
29 |
+
y otras mil vezes los braços.
|
30 |
+
Otra, y otras mil sean lazos
|
31 |
+
de nuestra antigua amistad.
|
32 |
+
Como venis?
|
33 |
+
Yo me siento
|
34 |
+
tan alegre, tan vfano,
|
35 |
+
tan venturoso, tan vano,
|
36 |
+
que no podrà el pensamiento
|
37 |
+
encareceros jamàs
|
38 |
+
las venturas que posseo,
|
39 |
+
porque el pensamiento creo [/INST]"""
|
40 |
+
|
41 |
model, tokenizer = load("versae/filiberto-7B-instruct")
|
42 |
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
43 |
```
|