初始化项目，由ModelHub XC社区提供模型
Model: llmware/slim-sql-1b-v0 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
93
README.md
Normal file
93
README.md
Normal file
@@ -0,0 +1,93 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
# Model Card for Model ID
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
|
||||
slim-sql-1b-v0 is the first model in the SLIM (Specialized Language Instruct Model) series.
|
||||
|
||||
### Benchmark Tests
|
||||
|
||||
Evaluated against 100 test SQL queries with under 100 characters. 1 point given for exact string match, 0 given for incorrect answer.
|
||||
|
||||
--**Accuracy Score**: **86** correct out of 100
|
||||
- 8 incorrect answers attributed to query structure ordering or naming convention differences
|
||||
- 6 incorrect answers attributed to incorrect variable selection or aggregate function use
|
||||
|
||||
### Model Description
|
||||
|
||||
<!-- Provide a longer summary of what this model is. -->
|
||||
|
||||
- **Developed by:** llmware
|
||||
- **Model type:** TinyLlama
|
||||
- **Language(s) (NLP):** English
|
||||
- **License:** apache-2.0
|
||||
- **Finetuned from model:** [TinyLlama-1.1b - 2.5T checkpoint](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1195k-token-2.5T)
|
||||
|
||||
|
||||
### Direct Use
|
||||
|
||||
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
||||
|
||||
slim-sql-1b-v0 is designed to generate accurate SQL queries for data retrieval on simple table structures given a natural language prompt.
|
||||
For best results, prompts should be structured as a question to retrieve information and perform aggregate functions on one or several variables.
|
||||
|
||||
## Bias, Risks, and Limitations
|
||||
|
||||
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
||||
|
||||
Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms.
|
||||
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
The fastest way to get started with slim is through direct import in transformers:
|
||||
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
tokenizer = AutoTokenizer.from_pretrained("slim-sql-1b-v0")
|
||||
model = AutoModelForCausalLM.from_pretrained("slim-sql-1b-v0")
|
||||
|
||||
Please refer to the generation_test.py files in the Files repository, which includes 100 samples and script to test the model.
|
||||
|
||||
The sql-slim model was fine-tuned with a simple "\<human> and \<bot> wrapper", so to get the best results, wrap inference entries as:
|
||||
|
||||
full_prompt = "<human>: " + my_prompt + "\n" + "<bot>:"
|
||||
|
||||
The prompt consists of two sub-parts:
|
||||
|
||||
1. Table creation prompt providing table name, variables, and variable type.
|
||||
2. Specific question or instruction based on the text passage
|
||||
|
||||
Test sample example: {"context": "CREATE TABLE table_name_34 (season VARCHAR, lost VARCHAR, points VARCHAR)", "question": "Which season did the Minnesota Kicks lose 13 games and score 156 points?", "answer": "SELECT COUNT(season) FROM table_name_34 WHERE lost = 13 AND points = 156"}
|
||||
A subset of test samples are provided in this repo ("sql_test_100_simple_s").
|
||||
|
||||
For use in training, the "\<human>" tag would be associated with "context" and "question" statements, while the "\<bot>" tag will be associated with the model's output.
|
||||
|
||||
If you are using a HuggingFace generation script:
|
||||
|
||||
# prepare prompt packaging used in fine-tuning process
|
||||
new_prompt = "<human>: " + entries["context"] + "\n" + entries["query"] + "\n" + "<bot>:"
|
||||
|
||||
inputs = tokenizer(new_prompt, return_tensors="pt")
|
||||
start_of_output = len(inputs.input_ids[0])
|
||||
|
||||
# temperature: set at 0.3 for consistency of output
|
||||
# max_new_tokens: set at 100 - may prematurely stop a few of the summaries
|
||||
|
||||
outputs = model.generate(
|
||||
inputs.input_ids.to(device),
|
||||
eos_token_id=tokenizer.eos_token_id,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
do_sample=True,
|
||||
temperature=0.3,
|
||||
max_new_tokens=100,
|
||||
)
|
||||
|
||||
output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True)
|
||||
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
Dylan Oberst & llmware team
|
||||
86
config.json
Normal file
86
config.json
Normal file
@@ -0,0 +1,86 @@
|
||||
{
|
||||
"aib_version": "",
|
||||
"training_dataset": "",
|
||||
"training_timestamp": "Mon Jan 1 00:46:42 2024",
|
||||
"training_comments": "shared_LLaMa-1.3B",
|
||||
"vocab_size": 32000,
|
||||
"max_position_embeddings": 2048,
|
||||
"hidden_size": 2048,
|
||||
"intermediate_size": 5632,
|
||||
"num_hidden_layers": 22,
|
||||
"num_attention_heads": 32,
|
||||
"num_key_value_heads": 4,
|
||||
"hidden_act": "silu",
|
||||
"initializer_range": 0.02,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"pretraining_tp": 1,
|
||||
"use_cache": true,
|
||||
"rope_theta": 10000.0,
|
||||
"rope_scaling": null,
|
||||
"attention_bias": false,
|
||||
"return_dict": true,
|
||||
"output_hidden_states": false,
|
||||
"output_attentions": false,
|
||||
"torchscript": false,
|
||||
"torch_dtype": "float32",
|
||||
"use_bfloat16": false,
|
||||
"tf_legacy_loss": false,
|
||||
"pruned_heads": {},
|
||||
"tie_word_embeddings": false,
|
||||
"is_encoder_decoder": false,
|
||||
"is_decoder": false,
|
||||
"cross_attention_hidden_size": null,
|
||||
"add_cross_attention": false,
|
||||
"tie_encoder_decoder": false,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"do_sample": false,
|
||||
"early_stopping": false,
|
||||
"num_beams": 1,
|
||||
"num_beam_groups": 1,
|
||||
"diversity_penalty": 0.0,
|
||||
"temperature": 1.0,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"typical_p": 1.0,
|
||||
"repetition_penalty": 1.0,
|
||||
"length_penalty": 1.0,
|
||||
"no_repeat_ngram_size": 0,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"bad_words_ids": null,
|
||||
"num_return_sequences": 1,
|
||||
"chunk_size_feed_forward": 0,
|
||||
"output_scores": false,
|
||||
"return_dict_in_generate": false,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"remove_invalid_values": false,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"suppress_tokens": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"finetuning_task": null,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"tokenizer_class": null,
|
||||
"prefix": null,
|
||||
"bos_token_id": 1,
|
||||
"pad_token_id": null,
|
||||
"eos_token_id": 2,
|
||||
"sep_token_id": null,
|
||||
"decoder_start_token_id": null,
|
||||
"task_specific_params": null,
|
||||
"problem_type": null,
|
||||
"_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
||||
"transformers_version": "4.35.2",
|
||||
"model_type": "llama",
|
||||
"trained": "custom training"
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"max_length": 2048,
|
||||
"transformers_version": "4.31.0.dev0"
|
||||
}
|
||||
102
generation_test_sql_slim_hf.py
Normal file
102
generation_test_sql_slim_hf.py
Normal file
@@ -0,0 +1,102 @@
|
||||
|
||||
import time
|
||||
import os
|
||||
import json
|
||||
from werkzeug.utils import secure_filename
|
||||
import re
|
||||
import ast
|
||||
import sqlite3
|
||||
import random
|
||||
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
from llmware.models import ModelCatalog
|
||||
from llmware.prompts import Prompt
|
||||
|
||||
def model_test_run_general():
|
||||
|
||||
t0 = time.time()
|
||||
|
||||
model_name = "llmware/slim-sql-1b-v0"
|
||||
|
||||
print("update: model_name - ", model_name)
|
||||
|
||||
custom_hf_model = AutoModelForCausalLM.from_pretrained(model_name,trust_remote_code=True)
|
||||
|
||||
hf_tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
# now, we have 'imported' our own custom 'instruct' model into llmware
|
||||
model = ModelCatalog().load_hf_generative_model(custom_hf_model, hf_tokenizer, instruction_following=False,
|
||||
prompt_wrapper="human_bot")
|
||||
|
||||
model.temperature = 0.3
|
||||
# run direct inference on model
|
||||
print("\nupdate: Starting Generative Instruct Custom Fine-tuned Test")
|
||||
|
||||
t1 = time.time()
|
||||
|
||||
print("update: time loading model - ", t1 - t0)
|
||||
|
||||
fp = ""
|
||||
fn = "sql_test_100_simple_s.jsonl"
|
||||
|
||||
opened_file = open(os.path.join(fp, fn), "r")
|
||||
|
||||
prompt_list = []
|
||||
|
||||
for i, rows in enumerate(opened_file):
|
||||
# print("update: ", i, rows)
|
||||
rows = json.loads(rows)
|
||||
new_entry = {"question": rows["question"],
|
||||
"answer": rows["answer"],
|
||||
"context": rows["context"]}
|
||||
|
||||
prompt_list.append(new_entry)
|
||||
|
||||
random.shuffle(prompt_list)
|
||||
|
||||
total_response_output = []
|
||||
perfect_match = 0
|
||||
|
||||
for i, entries in enumerate(prompt_list):
|
||||
prompt = entries["question"]
|
||||
context = re.sub("[\n\r]","", entries["context"])
|
||||
context = re.sub("\s+", " ", context)
|
||||
context = re.sub("\"", "", context)
|
||||
|
||||
answer = ""
|
||||
|
||||
if "answer" in entries:
|
||||
answer = entries["answer"]
|
||||
|
||||
output = model.inference(prompt, add_context=context, add_prompt_engineering=True)
|
||||
|
||||
print("\nupdate: model question - ", prompt)
|
||||
|
||||
llm_response = re.sub("['\"]", "", output["llm_response"])
|
||||
answer = re.sub("['\"]", "", answer)
|
||||
|
||||
print("update: model response - ", i, llm_response)
|
||||
print("update: model gold answer - ", answer)
|
||||
|
||||
if llm_response.strip().lower() == answer.strip().lower():
|
||||
perfect_match += 1
|
||||
print("update: 100% MATCH")
|
||||
|
||||
print("update: perfect match accuracy - ", perfect_match / (i+1))
|
||||
|
||||
core_output = {"number": i,
|
||||
"llm_response": output["llm_response"],
|
||||
"gold_answer": answer,
|
||||
"prompt": prompt,
|
||||
"usage": output["usage"]}
|
||||
|
||||
total_response_output.append(core_output)
|
||||
|
||||
t2 = time.time()
|
||||
|
||||
print("update: total processing time: ", t2-t1)
|
||||
|
||||
return total_response_output
|
||||
|
||||
output = model_test_run_general()
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:445d369ff039384b01fd0508aa5051c9e385d2c704bb28f480e4a697778f9586
|
||||
size 2200181102
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
100
sql_test_100_simple_s.jsonl
Normal file
100
sql_test_100_simple_s.jsonl
Normal file
@@ -0,0 +1,100 @@
|
||||
{"context": "CREATE TABLE table_25572068_1 ( location VARCHAR, winning_driver VARCHAR )", "question": "What was the location when the winning driver was Nathana l Berthon?", "answer": "SELECT location FROM table_25572068_1 WHERE winning_driver = \"Nathana\u00ebl Berthon\""}
|
||||
{"context": "CREATE TABLE table_20297668_1 (standard_yarn_weight_system VARCHAR, wraps_per_inch__wpi_ VARCHAR)", "question": "Name the standard yarn weight system for 7 wpi", "answer": "SELECT standard_yarn_weight_system FROM table_20297668_1 WHERE wraps_per_inch__wpi_ = \"7 wpi\""}
|
||||
{"context": "CREATE TABLE table_1805191_50 (district VARCHAR, party VARCHAR, first_elected VARCHAR)", "question": "What district first elected a Democratic incumbent in 1998?", "answer": "SELECT district FROM table_1805191_50 WHERE party = \"Democratic\" AND first_elected = 1998"}
|
||||
{"context": "CREATE TABLE table_name_60 (avg_g INTEGER, name VARCHAR, gain VARCHAR)", "question": "Which Avg/G has a Name of david allen, and a Gain larger than 371?", "answer": "SELECT AVG(avg_g) FROM table_name_60 WHERE name = \"david allen\" AND gain > 371"}
|
||||
{"context": "CREATE TABLE table_name_57 ( position INTEGER, points VARCHAR, drawn VARCHAR )", "question": "How many positions have 15 for the points, with a drawn less than 3?", "answer": "SELECT SUM(position) FROM table_name_57 WHERE points = 15 AND drawn < 3"}
|
||||
{"context": "CREATE TABLE table_name_4 ( home VARCHAR, attendance VARCHAR, away VARCHAR )", "question": "Who was the home team when real juventud was the away team when there were more than 1189 in attendance?", "answer": "SELECT home FROM table_name_4 WHERE attendance > 1189 AND away = \"real juventud\""}
|
||||
{"context": "CREATE TABLE table_1952065_4 ( teams_with_division_titles VARCHAR, division_championships VARCHAR )", "question": "How many division title teams were in the division championships 9 times?", "answer": "SELECT COUNT(teams_with_division_titles) FROM table_1952065_4 WHERE division_championships = 9"}
|
||||
{"context": "CREATE TABLE table_29728596_2 ( away_team VARCHAR, competition VARCHAR, home_team VARCHAR )", "question": "Who were the away teams when the competition was the 1st republic of srpska football day and the home team was u 14 republic of srpska?", "answer": "SELECT away_team FROM table_29728596_2 WHERE competition = \"1st ``Republic of Srpska Football Day``\" AND home_team = \"U 14 Republic of Srpska\""}
|
||||
{"context": "CREATE TABLE table_2104176_1 ( distinguished_service_cross VARCHAR, navy_cross VARCHAR )", "question": "What is the distinguished service cross when the navy cross is Coast Guard commendation medal?", "answer": "SELECT distinguished_service_cross FROM table_2104176_1 WHERE navy_cross = \"Coast Guard Commendation Medal\""}
|
||||
{"context": "CREATE TABLE table_name_9 ( tckl VARCHAR, year VARCHAR, p_ko_ret VARCHAR )", "question": "What is the total of TCKL in 2000 with a P/KO RET less than 14?", "answer": "SELECT COUNT(tckl) FROM table_name_9 WHERE year = \"2000\" AND p_ko_ret < 14"}
|
||||
{"context": "CREATE TABLE table_14312471_4 (ground VARCHAR, crowd VARCHAR)", "question": "What are the ground where the crowd totals 19929?", "answer": "SELECT ground FROM table_14312471_4 WHERE crowd = 19929"}
|
||||
{"context": "CREATE TABLE table_name_38 ( population INTEGER, name_of_city VARCHAR )", "question": "What is the population of Chimbote?", "answer": "SELECT SUM(population) FROM table_name_38 WHERE name_of_city = \"chimbote\""}
|
||||
{"context": "CREATE TABLE table_13762472_7 ( score VARCHAR, location_attendance VARCHAR )", "question": "What was the score when the heat played at charlotte arena?", "answer": "SELECT score FROM table_13762472_7 WHERE location_attendance = \"Charlotte Arena\""}
|
||||
{"context": "CREATE TABLE table_25058269_1 (runner_up VARCHAR, season VARCHAR)", "question": "In season 2007\u201308 who is the runner-up?", "answer": "SELECT runner_up FROM table_25058269_1 WHERE season = \"2007\u201308\""}
|
||||
{"context": "CREATE TABLE table_name_32 (transmission VARCHAR, trim VARCHAR)", "question": "What is the Removal that has a Trim of xe (2009)?", "answer": "SELECT transmission FROM table_name_32 WHERE trim = \"xe (2009)\""}
|
||||
{"context": "CREATE TABLE table_2343740_1 (title VARCHAR, original_air_date VARCHAR)", "question": "What was the title of the episode that aired February 9, 1979?", "answer": "SELECT title FROM table_2343740_1 WHERE original_air_date = \"February 9, 1979\""}
|
||||
{"context": "CREATE TABLE table_1876825_2 ( no_in_series VARCHAR, original_air_date VARCHAR )", "question": "Name the total number of series for march 19, 2000", "answer": "SELECT COUNT(no_in_series) FROM table_1876825_2 WHERE original_air_date = \"March 19, 2000\""}
|
||||
{"context": "CREATE TABLE table_name_83 ( class VARCHAR, year VARCHAR, stages_won VARCHAR, vehicle VARCHAR )", "question": "What class is associated with 0 stages won, a hummer, and before 2009?", "answer": "SELECT class FROM table_name_83 WHERE stages_won = \"0\" AND vehicle = \"hummer\" AND year < 2009"}
|
||||
{"context": "CREATE TABLE table_25920798_2 ( leader_battle VARCHAR, eliminated VARCHAR )", "question": "Name the leader battle for plamen", "answer": "SELECT leader_battle FROM table_25920798_2 WHERE eliminated = \"Plamen\""}
|
||||
{"context": "CREATE TABLE table_name_51 (attendance INTEGER, game_site VARCHAR, date VARCHAR)", "question": "What is the largest attendance at Memorial Stadium on December 12, 1965?", "answer": "SELECT MAX(attendance) FROM table_name_51 WHERE game_site = \"memorial stadium\" AND date = \"december 12, 1965\""}
|
||||
{"context": "CREATE TABLE table_name_95 ( colour_commentator_s_ VARCHAR, play_by_play VARCHAR )", "question": "Were the color commentators who worked with Bill Hewitt doing the play-by-play?", "answer": "SELECT colour_commentator_s_ FROM table_name_95 WHERE play_by_play = \"bill hewitt\""}
|
||||
{"context": "CREATE TABLE table_26555737_1 (result VARCHAR, director VARCHAR)", "question": "When hany abu-assad category:articles with hcards is the director what is the result?", "answer": "SELECT result FROM table_26555737_1 WHERE director = \"Hany Abu-Assad Category:Articles with hCards\""}
|
||||
{"context": "CREATE TABLE table_name_96 ( entered VARCHAR, finished VARCHAR )", "question": "What day did the celebrity who finished 4th enter?", "answer": "SELECT entered FROM table_name_96 WHERE finished = \"4th\""}
|
||||
{"context": "CREATE TABLE table_27723228_8 (high_rebounds VARCHAR, game VARCHAR)", "question": "How many people are listed for high rebounds on game 30?", "answer": "SELECT COUNT(high_rebounds) FROM table_27723228_8 WHERE game = 30"}
|
||||
{"context": "CREATE TABLE table_name_13 (australian_marquee VARCHAR, captain VARCHAR)", "question": "What Australian Marquee team is Michael Beauchamp a captain of?", "answer": "SELECT australian_marquee FROM table_name_13 WHERE captain = \"michael beauchamp\""}
|
||||
{"context": "CREATE TABLE table_17257687_1 ( event_2 VARCHAR, event_1 VARCHAR )", "question": "What was event 2 when event 1 was Atlasphere?", "answer": "SELECT event_2 FROM table_17257687_1 WHERE event_1 = \"Atlasphere\""}
|
||||
{"context": "CREATE TABLE table_name_87 ( d_48_\u221a VARCHAR, d_46_\u221a VARCHAR )", "question": "What is the D 48 with a D 46 with r 33 o?", "answer": "SELECT d_48_\u221a FROM table_name_87 WHERE d_46_\u221a = \"r 33 o\""}
|
||||
{"context": "CREATE TABLE table_name_59 (party VARCHAR, name VARCHAR)", "question": "What is the party of Richard Simpson?", "answer": "SELECT party FROM table_name_59 WHERE name = \"richard simpson\""}
|
||||
{"context": "CREATE TABLE table_name_15 ( city_of_license VARCHAR, frequency VARCHAR )", "question": "What is the city of license for the frequency 90.1 FM?", "answer": "SELECT city_of_license FROM table_name_15 WHERE frequency = \"90.1 fm\""}
|
||||
{"context": "CREATE TABLE table_name_45 ( engine VARCHAR, chassis VARCHAR, rank VARCHAR )", "question": "What engine was used by the teams that used a Lola b02/00 chassis and ranked 1st?", "answer": "SELECT engine FROM table_name_45 WHERE chassis = \"lola b02/00\" AND rank = \"1st\""}
|
||||
{"context": "CREATE TABLE table_name_93 (attendance INTEGER, round VARCHAR)", "question": "What is the highest attendance among Group E games?", "answer": "SELECT MAX(attendance) FROM table_name_93 WHERE round = \"group e\""}
|
||||
{"context": "CREATE TABLE table_name_53 (gold VARCHAR, year VARCHAR, location VARCHAR)", "question": "Who got the gold in seoul before 2002?", "answer": "SELECT gold FROM table_name_53 WHERE year < 2002 AND location = \"seoul\""}
|
||||
{"context": "CREATE TABLE table_name_3 ( margin INTEGER, round VARCHAR )", "question": "What is the average Margin that has a Round of 13. (h)?", "answer": "SELECT AVG(margin) FROM table_name_3 WHERE round = \"13. (h)\""}
|
||||
{"context": "CREATE TABLE table_name_39 (fastest_lap VARCHAR, constructor VARCHAR, location VARCHAR)", "question": "Who ran the fastest lap in the team that competed in Zolder, in which Ferrari was the Constructor?", "answer": "SELECT fastest_lap FROM table_name_39 WHERE constructor = \"ferrari\" AND location = \"zolder\""}
|
||||
{"context": "CREATE TABLE settlements (settlement_amount INTEGER)", "question": "What are the maximum and minimum settlement amount on record?", "answer": "SELECT MAX(settlement_amount), MIN(settlement_amount) FROM settlements"}
|
||||
{"context": "CREATE TABLE table_name_50 (quantity INTEGER, type VARCHAR, retired VARCHAR)", "question": "What is the lowest quantity of the 1b n2 type, which was retired in 1907-12?", "answer": "SELECT MIN(quantity) FROM table_name_50 WHERE type = \"1b n2\" AND retired = \"1907-12\""}
|
||||
{"context": "CREATE TABLE Rooms (roomName VARCHAR, bedType VARCHAR, decor VARCHAR)", "question": "List the type of bed and name of all traditional rooms.", "answer": "SELECT roomName, bedType FROM Rooms WHERE decor = \"traditional\""}
|
||||
{"context": "CREATE TABLE table_25740774_1 (f_laps VARCHAR, team VARCHAR)", "question": "How many flaps are there for the team march 3 racing (1-4) top speed racing team (5-12)?", "answer": "SELECT COUNT(f_laps) FROM table_25740774_1 WHERE team = \"March 3 Racing (1-4) Top Speed Racing team (5-12)\""}
|
||||
{"context": "CREATE TABLE table_name_18 (frequency VARCHAR, format VARCHAR)", "question": "What is the frequency for the active rock format?", "answer": "SELECT frequency FROM table_name_18 WHERE format = \"active rock\""}
|
||||
{"context": "CREATE TABLE table_11665016_2 (title VARCHAR, written_by VARCHAR)", "question": "Which episode was written by anthony e. zuiker & ken solarz", "answer": "SELECT title FROM table_11665016_2 WHERE written_by = \"Anthony E. Zuiker & Ken Solarz\""}
|
||||
{"context": "CREATE TABLE table_name_36 ( score_in_the_final VARCHAR, date VARCHAR )", "question": "What was the score in the final on 14 august 1994?", "answer": "SELECT score_in_the_final FROM table_name_36 WHERE date = \"14 august 1994\""}
|
||||
{"context": "CREATE TABLE table_name_98 ( sodium VARCHAR, rubidium VARCHAR )", "question": "what is the properties of sodium when rubidium is nacl (2.1)?", "answer": "SELECT sodium FROM table_name_98 WHERE rubidium = \"nacl (2.1)\""}
|
||||
{"context": "CREATE TABLE table_name_16 ( opponent VARCHAR, result VARCHAR )", "question": "Which Opponent has a Result of l 24 3?", "answer": "SELECT opponent FROM table_name_16 WHERE result = \"l 24\u20133\""}
|
||||
{"context": "CREATE TABLE table_name_59 (Id VARCHAR)", "question": "What is the 2003 value with 2r in 2008 and 1r in 2011?", "answer": "SELECT 2003 FROM table_name_59 WHERE 2008 = \"2r\" AND 2011 = \"1r\""}
|
||||
{"context": "CREATE TABLE table_26914076_4 (directed_by VARCHAR, us_viewers__millions_ VARCHAR)", "question": "Who directed the episode that had 0.54 million U.S. viewers? ", "answer": "SELECT directed_by FROM table_26914076_4 WHERE us_viewers__millions_ = \"0.54\""}
|
||||
{"context": "CREATE TABLE table_name_57 (team VARCHAR, points VARCHAR)", "question": "How much 1991-1992 has a Team of gimnasia de la plata, and more than 113 points?", "answer": "SELECT COUNT(1991 AS _1992) FROM table_name_57 WHERE team = \"gimnasia de la plata\" AND points > 113"}
|
||||
{"context": "CREATE TABLE table_name_62 (size__steps_ INTEGER, interval_name VARCHAR)", "question": "Tell me the average size for minor third", "answer": "SELECT AVG(size__steps_) FROM table_name_62 WHERE interval_name = \"minor third\""}
|
||||
{"context": "CREATE TABLE table_2417340_4 (successor VARCHAR, vacator VARCHAR, district VARCHAR)", "question": "What was the successor for vacant alabama 3rd?", "answer": "SELECT successor FROM table_2417340_4 WHERE vacator = \"Vacant\" AND district = \"Alabama 3rd\""}
|
||||
{"context": "CREATE TABLE table_name_92 (winner VARCHAR, finalist VARCHAR)", "question": "Who was the winner against finalist Lina Krasnoroutskaya?", "answer": "SELECT winner FROM table_name_92 WHERE finalist = \"lina krasnoroutskaya\""}
|
||||
{"context": "CREATE TABLE table_name_74 ( car__number VARCHAR, make VARCHAR, driver VARCHAR )", "question": "What is Mike Skinner's Chevrolet's Car #?", "answer": "SELECT COUNT(car__number) FROM table_name_74 WHERE make = \"chevrolet\" AND driver = \"mike skinner\""}
|
||||
{"context": "CREATE TABLE table_name_73 ( school VARCHAR, indoor_track VARCHAR, soccer VARCHAR, tennis VARCHAR )", "question": "Which school has yes for soccer, tennis and indoor track.", "answer": "SELECT school FROM table_name_73 WHERE soccer = \"yes\" AND tennis = \"yes\" AND indoor_track = \"yes\""}
|
||||
{"context": "CREATE TABLE table_name_63 (chip VARCHAR, frequency_ VARCHAR, mhz VARCHAR)", "question": "Tell me the chip with frequency larger than 10", "answer": "SELECT chip FROM table_name_63 WHERE frequency_[mhz] > 10"}
|
||||
{"context": "CREATE TABLE table_25662434_1 (title VARCHAR, production_code VARCHAR)", "question": "How many titles had production code 1040?", "answer": "SELECT COUNT(title) FROM table_25662434_1 WHERE production_code = 1040"}
|
||||
{"context": "CREATE TABLE table_14342210_14 ( touchdowns__5_points_ INTEGER, player VARCHAR )", "question": "How many touchdowns did Bruce Shorts make?", "answer": "SELECT MAX(touchdowns__5_points_) FROM table_14342210_14 WHERE player = \"Bruce Shorts\""}
|
||||
{"context": "CREATE TABLE table_name_28 ( home_team VARCHAR, venue VARCHAR )", "question": "What team plays at home at Windy Hill?", "answer": "SELECT home_team FROM table_name_28 WHERE venue = \"windy hill\""}
|
||||
{"context": "CREATE TABLE table_27986200_3 ( match_points VARCHAR, eliminated_from_competition VARCHAR )", "question": "What were the match points when Bordeaux-B gles was eliminated from competition?", "answer": "SELECT match_points FROM table_27986200_3 WHERE eliminated_from_competition = \"Bordeaux-B\u00e8gles\""}
|
||||
{"context": "CREATE TABLE table_name_89 ( bronze INTEGER, total VARCHAR, rank VARCHAR, nation VARCHAR )", "question": "Which is the highest bronze at Chinese Taipei when the rank was higher than 5 and total was smaller than 1?", "answer": "SELECT MAX(bronze) FROM table_name_89 WHERE rank > 5 AND nation = \"chinese taipei\" AND total < 1"}
|
||||
{"context": "CREATE TABLE entrepreneur ( Investor VARCHAR )", "question": "What are the investors of entrepreneurs and the corresponding number of entrepreneurs invested by each investor?", "answer": "SELECT Investor, COUNT(*) FROM entrepreneur GROUP BY Investor"}
|
||||
{"context": "CREATE TABLE table_22319599_1 (team_name VARCHAR, school VARCHAR)", "question": "If the school is Rend Lake College, what is the team name?", "answer": "SELECT team_name FROM table_22319599_1 WHERE school = \"Rend Lake College\""}
|
||||
{"context": "CREATE TABLE table_17058116_6 (record VARCHAR, team VARCHAR)", "question": "How many times did the team play charlotte?", "answer": "SELECT COUNT(record) FROM table_17058116_6 WHERE team = \"Charlotte\""}
|
||||
{"context": "CREATE TABLE table_name_56 ( game VARCHAR, series VARCHAR )", "question": "What is the game number for series 4-2?", "answer": "SELECT COUNT(game) FROM table_name_56 WHERE series = \"4-2\""}
|
||||
{"context": "CREATE TABLE table_name_11 (name VARCHAR, points VARCHAR, games VARCHAR, rank VARCHAR)", "question": "What is Name, when Games are less than 38, when Rank is less than 4, and when Points are 357?", "answer": "SELECT name FROM table_name_11 WHERE games < 38 AND rank < 4 AND points = 357"}
|
||||
{"context": "CREATE TABLE entrepreneur (Id VARCHAR)", "question": "How many entrepreneurs are there?", "answer": "SELECT COUNT(*) FROM entrepreneur"}
|
||||
{"context": "CREATE TABLE table_name_15 (year VARCHAR, label VARCHAR, type VARCHAR)", "question": "Name the Year which has a Label of atco records and a Type of album? Question 2", "answer": "SELECT year FROM table_name_15 WHERE label = \"atco records\" AND type = \"album\""}
|
||||
{"context": "CREATE TABLE table_2468961_7 ( production_code VARCHAR, no_in_series VARCHAR )", "question": "When 137 is the number in series what is the production code?", "answer": "SELECT production_code FROM table_2468961_7 WHERE no_in_series = 137"}
|
||||
{"context": "CREATE TABLE table_name_80 (no_result INTEGER, lost VARCHAR, _percentage_win_ VARCHAR, a_ VARCHAR)", "question": "What is the low no result with more than 5 loss and a win ration lesser than 58.06?", "answer": "SELECT MIN(no_result) FROM table_name_80 WHERE lost > 5 AND _percentage_win_[a_] < 58.06"}
|
||||
{"context": "CREATE TABLE table_name_13 ( winning_driver VARCHAR, circuit VARCHAR )", "question": "Which Driver won the Circuit of Rio de Janeiro?", "answer": "SELECT winning_driver FROM table_name_13 WHERE circuit = \"rio de janeiro\""}
|
||||
{"context": "CREATE TABLE table_1353096_2 ( station VARCHAR, city_of_license_market VARCHAR )", "question": "Which station has a license in Fort Collins, Colorado?", "answer": "SELECT station FROM table_1353096_2 WHERE city_of_license_market = \"Fort Collins, Colorado\""}
|
||||
{"context": "CREATE TABLE table_name_64 ( writer_s_ VARCHAR, recorded_at VARCHAR, time VARCHAR )", "question": "Who wrote the album recorded at funhouse studios with a time of 3:27?", "answer": "SELECT writer_s_ FROM table_name_64 WHERE recorded_at = \"funhouse studios\" AND time = \"3:27\""}
|
||||
{"context": "CREATE TABLE table_name_26 (home_team VARCHAR, away_team VARCHAR)", "question": "Who was North Melbourne's home opponent?", "answer": "SELECT home_team FROM table_name_26 WHERE away_team = \"north melbourne\""}
|
||||
{"context": "CREATE TABLE table_1140082_2 (constructor VARCHAR, race VARCHAR)", "question": "What is the constructor of the Swedish Grand Prix?", "answer": "SELECT constructor FROM table_1140082_2 WHERE race = \"Swedish Grand Prix\""}
|
||||
{"context": "CREATE TABLE table_name_74 (player VARCHAR, position VARCHAR, school_club_team VARCHAR)", "question": "What Utah Jazz Forward played for Southern Methodist?", "answer": "SELECT player FROM table_name_74 WHERE position = \"forward\" AND school_club_team = \"southern methodist\""}
|
||||
{"context": "CREATE TABLE table_name_42 (martin VARCHAR, lanier VARCHAR)", "question": "What martin has a lanier of 6%?", "answer": "SELECT martin FROM table_name_42 WHERE lanier = \"6%\""}
|
||||
{"context": "CREATE TABLE table_name_34 (venue VARCHAR, date VARCHAR)", "question": "WHAT IS THE VENUE ON MARCH 28, 2008?", "answer": "SELECT venue FROM table_name_34 WHERE date = \"march 28, 2008\""}
|
||||
{"context": "CREATE TABLE table_name_30 (order__number VARCHAR, result VARCHAR, original_artist VARCHAR)", "question": "In what order were the Bee Gees as the artist when it was a result of bottom 3?", "answer": "SELECT order__number FROM table_name_30 WHERE result = \"bottom 3\" AND original_artist = \"bee gees\""}
|
||||
{"context": "CREATE TABLE Cartoon (Written_by VARCHAR)", "question": "How many cartoons were written by \"Joseph Kuhr\"?", "answer": "SELECT COUNT(*) FROM Cartoon WHERE Written_by = \"Joseph Kuhr\""}
|
||||
{"context": "CREATE TABLE table_15887683_6 ( country VARCHAR, television_service VARCHAR )", "question": "Name the country for sky primafila 7 hd", "answer": "SELECT country FROM table_15887683_6 WHERE television_service = \"Sky Primafila 7 HD\""}
|
||||
{"context": "CREATE TABLE table_name_35 (surface VARCHAR, partner VARCHAR)", "question": "What was the surface for the game that was played with partner Tiya Rolle?", "answer": "SELECT surface FROM table_name_35 WHERE partner = \"tiya rolle\""}
|
||||
{"context": "CREATE TABLE table_name_13 ( opponent VARCHAR, res VARCHAR, time VARCHAR )", "question": "Who is the opponent of the match with a win result and a time of 3:02?", "answer": "SELECT opponent FROM table_name_13 WHERE res = \"win\" AND time = \"3:02\""}
|
||||
{"context": "CREATE TABLE table_name_18 (affiliation VARCHAR, district VARCHAR)", "question": "What is the affiliation for the Cuddalore District?", "answer": "SELECT affiliation FROM table_name_18 WHERE district = \"cuddalore district\""}
|
||||
{"context": "CREATE TABLE table_name_77 ( wickets VARCHAR, average VARCHAR, runs VARCHAR, matches VARCHAR )", "question": "How many wickets have runs under 7531, matches over 44, and an average of 22.17?", "answer": "SELECT wickets FROM table_name_77 WHERE runs < 7531 AND matches > 44 AND average = 22.17"}
|
||||
{"context": "CREATE TABLE table_1243601_1 (playoffs VARCHAR, year VARCHAR)", "question": "What was the playoff result in 2002?", "answer": "SELECT playoffs FROM table_1243601_1 WHERE year = \"2002\""}
|
||||
{"context": "CREATE TABLE table_22043925_1 (school VARCHAR, location VARCHAR)", "question": "What is every school for the Adelaide location?", "answer": "SELECT school FROM table_22043925_1 WHERE location = \"Adelaide\""}
|
||||
{"context": "CREATE TABLE table_name_34 ( club VARCHAR, stadium VARCHAR )", "question": "What club does the stadium stc krymteplitsia belong to?", "answer": "SELECT club FROM table_name_34 WHERE stadium = \"stc krymteplitsia\""}
|
||||
{"context": "CREATE TABLE table_23696862_6 ( wsop_bracelets INTEGER )", "question": "What is the smallest amount of WSOP bracelets anyone had?", "answer": "SELECT MIN(wsop_bracelets) FROM table_23696862_6"}
|
||||
{"context": "CREATE TABLE table_name_5 ( date VARCHAR, opponent VARCHAR )", "question": "What is the Date of the game against Christo Van Rensburg?", "answer": "SELECT date FROM table_name_5 WHERE opponent = \"christo van rensburg\""}
|
||||
{"context": "CREATE TABLE table_name_75 (insurgents VARCHAR, civilians VARCHAR)", "question": "Name the insurgents for civilians being 49", "answer": "SELECT insurgents FROM table_name_75 WHERE civilians = \"49\""}
|
||||
{"context": "CREATE TABLE table_59552 ( \"Rider\" text, \"Bike\" text, \"Laps\" real, \"Time\" text, \"Grid\" real )", "question": "What is the highest Laps, when Bike is 'Yamaha YZF-R1', when Rider is 'David Checa', and when Grid is greater than 18?", "answer": "SELECT MAX(\"Laps\") FROM table_59552 WHERE \"Bike\" = 'yamaha yzf-r1' AND \"Rider\" = 'david checa' AND \"Grid\" > '18'"}
|
||||
{"context": "CREATE TABLE table_28014096_1 ( no_in_season INTEGER, production_code VARCHAR )", "question": "What is the number of this season's episode that had the production code 2t6206?", "answer": "SELECT MIN(no_in_season) FROM table_28014096_1 WHERE production_code = \"2T6206\""}
|
||||
{"context": "CREATE TABLE table_name_11 ( lane INTEGER, rank INTEGER )", "question": "What are the total lanes that have a rank larger than 22?", "answer": "SELECT SUM(lane) FROM table_name_11 WHERE rank > 22"}
|
||||
{"context": "CREATE TABLE table_name_10 (date VARCHAR, visitor VARCHAR)", "question": "What date was the game where the visiting team was philadelphia?", "answer": "SELECT date FROM table_name_10 WHERE visitor = \"philadelphia\""}
|
||||
{"context": "CREATE TABLE table_name_95 (height VARCHAR, name VARCHAR)", "question": "What is Height, when Name is \"Manuela Zanchi\"?", "answer": "SELECT height FROM table_name_95 WHERE name = \"manuela zanchi\""}
|
||||
{"context": "CREATE TABLE table_18042409_1 ( player VARCHAR, national_lacrosse_league VARCHAR )", "question": "List all of the NLL Toronto Rock players.", "answer": "SELECT player FROM table_18042409_1 WHERE national_lacrosse_league = \"Toronto Rock\""}
|
||||
{"context": "CREATE TABLE table_name_34 ( incumbent VARCHAR, first_elected VARCHAR, district VARCHAR )", "question": "Who is the incumbent for the Oregon 5 District that was elected in 1996?", "answer": "SELECT incumbent FROM table_name_34 WHERE first_elected = 1996 AND district = \"oregon 5\""}
|
||||
{"context": "CREATE TABLE table_1350350_2 ( rank INTEGER, per_capita_income VARCHAR )", "question": "what is the maximum rank with per capita income being $17,013", "answer": "SELECT MAX(rank) FROM table_1350350_2 WHERE per_capita_income = \"$17,013\""}
|
||||
{"context": "CREATE TABLE table_name_70 (rank INTEGER, gold INTEGER)", "question": "What is the rank where the gold is 0?", "answer": "SELECT AVG(rank) FROM table_name_70 WHERE gold < 0"}
|
||||
{"context": "CREATE TABLE table_name_56 (catalog VARCHAR, region VARCHAR)", "question": "What is the Catalog with a Region that is europe?", "answer": "SELECT catalog FROM table_name_56 WHERE region = \"europe\""}
|
||||
{"context": "CREATE TABLE table_name_23 (crowd INTEGER, home_team VARCHAR)", "question": "What was the crowd number when the home team was Carlton?", "answer": "SELECT MIN(crowd) FROM table_name_23 WHERE home_team = \"carlton\""}
|
||||
{"context": "CREATE TABLE table_name_15 (high_rebounds VARCHAR, date VARCHAR)", "question": "Who had the highest rebounds of the game on April 7?", "answer": "SELECT high_rebounds FROM table_name_15 WHERE date = \"april 7\""}
|
||||
{"context": "CREATE TABLE table_name_60 (win_loss VARCHAR, win__percentage VARCHAR)", "question": "What is Win-Loss, when Win % is .456?", "answer": "SELECT win_loss FROM table_name_60 WHERE win__percentage = \".456\""}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user