File size: 3,316 Bytes
d19a3de 5b4b3ce d19a3de 5b4b3ce c4a7a1e 5b4b3ce c4a7a1e 5b4b3ce d19a3de |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
---
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: Mistral-7B-text-to-sql-without-flash-attention-2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Mistral-7B-text-to-sql-without-flash-attention-2
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
with dataset b-mc2/sql-create-context
## Model description
More information needed
### Testing results
import torch
from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer, pipeline
peft_model_id = "frankmorales2020/Mistral-7B-text-to-sql-without-flash-attention-2"
model = AutoPeftModelForCausalLM.from_pretrained(
peft_model_id,
device_map="auto",
torch_dtype=torch.float16
)
tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
CASE Number 1:
prompt='What was the first album Beyoncé released as a solo artist?'
prompt = f"Instruct: generate a SQL query.\n{prompt}\nOutput:\n" # for dataset b-mc2/sql-create-context
outputs = pipe(prompt, max_new_tokens=1024, do_sample=True, temperature=0.9, top_k=50, top_p=0.1, eos_token_id=pipe.tokenizer.eos_token_id, pad_token_id=pipe.tokenizer.eos_token_id)
print('Question: %s'%prompt)
#print('Answer: %s \nOutput:\n'%outputs[0]['generated_text'])
print(f"Generated Answer:\n{outputs[0]['generated_text'][len(prompt):].strip()}")
Question: Instruct: generate a SQL query.
What was the first album Beyoncé released as a solo artist?
Output:
Generated Answer:
SELECT first_album FROM table_name_82 WHERE solo_artist = "beyoncé"
CASE Number 2:
prompt='What was the first album Beyoncé released as a solo artist?'
prompt = f"Instruct: Answer the following question.\n{prompt}\nOutput:\n"
outputs = pipe(prompt, max_new_tokens=1024, do_sample=True, temperature=0.9, top_k=50, top_p=0.1, eos_token_id=pipe.tokenizer.eos_token_id, pad_token_id=pipe.tokenizer.eos_token_id)
print('Question: %s'%prompt)
#print('Answer: %s \nOutput:\n'%outputs[0]['generated_text'])
print(f"Generated Answer:\n{outputs[0]['generated_text'][len(prompt):].strip()}")
Question: Instruct: Answer the following question.
What was the first album Beyoncé released as a solo artist?
Output:
Generated Answer:
The first album Beyoncé released as a solo artist was "Dangerously in Love".
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
### Training results
### Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2 |