surajgorai
commited on
Commit
•
689adba
1
Parent(s):
326f02d
update model card
Browse files
README.md
CHANGED
@@ -20,3 +20,49 @@ base_model: unsloth/llama-3-8b-bnb-4bit
|
|
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)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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)
|
23 |
+
|
24 |
+
|
25 |
+
## Usage
|
26 |
+
|
27 |
+
|
28 |
+
```python
|
29 |
+
from unsloth import FastLanguageModel
|
30 |
+
from unsloth import FastLanguageModel
|
31 |
+
import torch
|
32 |
+
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
|
33 |
+
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
|
34 |
+
load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.
|
35 |
+
model, tokenizer = FastLanguageModel.from_pretrained(
|
36 |
+
model_name = "surajgorai/llama_3_8b_text_to_sql_model", # YOUR MODEL YOU USED FOR TRAINING
|
37 |
+
max_seq_length = max_seq_length,
|
38 |
+
dtype = dtype,
|
39 |
+
load_in_4bit = load_in_4bit,
|
40 |
+
)
|
41 |
+
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
|
42 |
+
|
43 |
+
prompt = """You are a powerful text-to-SQL model. Your job is to answer questions about a database. You are given a question and context regarding one or more tables.
|
44 |
+
|
45 |
+
You must output the SQL query that answers the question.
|
46 |
+
|
47 |
+
### Instruction:
|
48 |
+
{}
|
49 |
+
|
50 |
+
### Input:
|
51 |
+
{}
|
52 |
+
|
53 |
+
### Response:
|
54 |
+
{}"""
|
55 |
+
|
56 |
+
# alpaca_prompt = You MUST copy from above!
|
57 |
+
inputs = tokenizer(
|
58 |
+
[
|
59 |
+
prompt.format(
|
60 |
+
'Name the result/games for 54741', # instruction
|
61 |
+
'CREATE TABLE table_21436373_11 (result_games VARCHAR, attendance VARCHAR)', # input
|
62 |
+
"", # output - leave this blank for generation!
|
63 |
+
)
|
64 |
+
], return_tensors = "pt").to("cuda")
|
65 |
+
|
66 |
+
outputs = model.generate(**inputs, max_new_tokens = 64, use_cache = True)
|
67 |
+
tokenizer.batch_decode(outputs)
|
68 |
+
```
|