初始化项目，由ModelHub XC社区提供模型
Model: skshmjn/llama-3.2-1B-Mongo-query-generator Source: Original Platform
This commit is contained in:
ModelHub XC
40
.gitattributes
vendored
Normal file
40
.gitattributes
vendored
Normal file
@@ -0,0 +1,40 @@
|
||||
*.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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
56
README.md
Normal file
56
README.md
Normal file
@@ -0,0 +1,56 @@
|
||||
---
|
||||
base_model: unsloth/Llama-3.2-1B-Instruct
|
||||
tags:
|
||||
- text-generation
|
||||
- mongodb
|
||||
- query-generation
|
||||
- transformers
|
||||
- unsloth
|
||||
- llama
|
||||
- trl
|
||||
- gguf
|
||||
- quantized
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
datasets:
|
||||
- skshmjn/mongo_prompt_query
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# MongoDB Query Generator - Llama-3.2-1B (Fine-tuned)
|
||||
|
||||
- **Developed by:** skshmjn
|
||||
- **License:** apache-2.0
|
||||
- **Finetuned from model:** [unsloth/Llama-3.2-1B-Instruct](https://huggingface.co/unsloth/Llama-3.2-1B-Instruct)
|
||||
- **Dataset Used:** [skshmjn/mongodb-chat-query](https://huggingface.co/datasets/skshmjn/mongodb-chat-query)
|
||||
- **Supports:** Transformers & GGUF (for fast inference on CPU/GPU)
|
||||
|
||||
## 🚀 **Model Overview**
|
||||
This model is designed to **generate MongoDB queries** from natural language prompts. It supports:
|
||||
- **Basic CRUD operations:** `find`, `insert`, `update`, `delete`
|
||||
- **Aggregation Pipelines:** `$group`, `$match`, `$lookup`, `$sort`, etc.
|
||||
- **Indexing & Performance Queries**
|
||||
- **Nested Queries & Joins (`$lookup`)**
|
||||
|
||||
Trained using **Unsloth** for efficient fine-tuning and **GGUF quantization** for fast inference.
|
||||
|
||||
---
|
||||
|
||||
## 📌 **Example Usage (Transformers)**
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "skshmjn/Llama-3.2-1B-Mongo-Instruct"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name)
|
||||
schema = {} # Pass your mongodb schema here, leave empty for generic queries. Sample available in hugging face's repository
|
||||
|
||||
prompt = "Here is mongodb schema {schema} and Find all employees older than 30 in the 'employees' collection."
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
|
||||
output = model.generate(**inputs, max_length=100)
|
||||
query = tokenizer.decode(output[0], skip_special_tokens=True)
|
||||
|
||||
print(query)
|
||||
3
config.json
Normal file
3
config.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"model_type": "llama"
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"max_length": 131072,
|
||||
"pad_token_id": 128004,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.49.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9a65e4b48855616d7736ee65eaecc2b1f2933506a0d74ed87bd3a73d6c1054ef
|
||||
size 2471645464
|
||||
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:fd012ab324f25663bc9dd9d1075e4859d68113aeb4c322c16ea232aeeb7c21ec
|
||||
size 2471678098
|
||||
224
sample_schama.json
Normal file
224
sample_schama.json
Normal file
@@ -0,0 +1,224 @@
|
||||
{
|
||||
"database": {
|
||||
"name": "customer360_retail_db",
|
||||
"collections": [
|
||||
{
|
||||
"name": "customers",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"customer_id": "String",
|
||||
"first_name": "String",
|
||||
"last_name": "String",
|
||||
"email": "String",
|
||||
"phone": "String",
|
||||
"date_of_birth": "Date",
|
||||
"gender": "String",
|
||||
"registration_date": "Date",
|
||||
"customer_segment": "String",
|
||||
"preferences": "Array",
|
||||
"address": {
|
||||
"street": "String",
|
||||
"city": "String",
|
||||
"state": "String",
|
||||
"zipcode": "String",
|
||||
"country": "String"
|
||||
},
|
||||
"opt_in_marketing": "Boolean",
|
||||
"created_at": "Date",
|
||||
"updated_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"customer_id": 1, "unique": true},
|
||||
{"email": 1, "unique": true},
|
||||
{"phone": 1},
|
||||
{"customer_segment": 1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "transactions",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"transaction_id": "String",
|
||||
"customer_id": "String",
|
||||
"transaction_date": "Date",
|
||||
"items_purchased": [
|
||||
{
|
||||
"product_id": "String",
|
||||
"product_name": "String",
|
||||
"category": "String",
|
||||
"quantity": "Int",
|
||||
"price": "Double"
|
||||
}
|
||||
],
|
||||
"payment_method": "String",
|
||||
"total_amount": "Double",
|
||||
"store_id": "String",
|
||||
"channel": "String",
|
||||
"created_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"transaction_id": 1, "unique": true},
|
||||
{"customer_id": 1},
|
||||
{"transaction_date": -1},
|
||||
{"store_id": 1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "products",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"product_id": "String",
|
||||
"name": "String",
|
||||
"description": "String",
|
||||
"category": "String",
|
||||
"sub_category": "String",
|
||||
"brand": "String",
|
||||
"price": "Double",
|
||||
"available": "Boolean",
|
||||
"created_at": "Date",
|
||||
"updated_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"product_id": 1, "unique": true},
|
||||
{"category": 1},
|
||||
{"brand": 1},
|
||||
{"available": 1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "web_activities",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"activity_id": "String",
|
||||
"customer_id": "String",
|
||||
"session_id": "String",
|
||||
"activity_type": "String",
|
||||
"page_url": "String",
|
||||
"referrer": "String",
|
||||
"device": {
|
||||
"device_type": "String",
|
||||
"browser": "String",
|
||||
"os": "String"
|
||||
},
|
||||
"activity_timestamp": "Date",
|
||||
"metadata": "Object",
|
||||
"created_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"activity_id": 1, "unique": true},
|
||||
{"customer_id": 1},
|
||||
{"session_id": 1},
|
||||
{"activity_type": 1},
|
||||
{"activity_timestamp": -1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "marketing_campaigns",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"campaign_id": "String",
|
||||
"name": "String",
|
||||
"description": "String",
|
||||
"start_date": "Date",
|
||||
"end_date": "Date",
|
||||
"channels": "Array",
|
||||
"segment_targets": "Array",
|
||||
"status": "String",
|
||||
"budget": "Double",
|
||||
"spent": "Double",
|
||||
"performance_metrics": "Object",
|
||||
"created_at": "Date",
|
||||
"updated_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"campaign_id": 1, "unique": true},
|
||||
{"name": 1},
|
||||
{"status": 1},
|
||||
{"start_date": -1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "support_interactions",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"interaction_id": "String",
|
||||
"customer_id": "String",
|
||||
"date": "Date",
|
||||
"channel": "String",
|
||||
"support_agent": "String",
|
||||
"reason": "String",
|
||||
"resolution_status": "String",
|
||||
"resolution_time_minutes": "Int",
|
||||
"notes": "String",
|
||||
"created_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"interaction_id": 1, "unique": true},
|
||||
{"customer_id": 1},
|
||||
{"date": -1},
|
||||
{"resolution_status": 1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "loyalty_program",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"customer_id": "String",
|
||||
"loyalty_number": "String",
|
||||
"points": "Int",
|
||||
"membership_tier": "String",
|
||||
"enrolled_date": "Date",
|
||||
"last_activity_date": "Date",
|
||||
"rewards_redeemed": "Array",
|
||||
"created_at": "Date",
|
||||
"updated_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"customer_id": 1, "unique": true},
|
||||
{"loyalty_number": 1, "unique": true},
|
||||
{"membership_tier": 1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "analytics_reports",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"report_id": "String",
|
||||
"generated_date": "Date",
|
||||
"report_type": "String",
|
||||
"time_period": {
|
||||
"start_date": "Date",
|
||||
"end_date": "Date"
|
||||
},
|
||||
"parameters": "Object",
|
||||
"result": "Object",
|
||||
"generated_by": "String",
|
||||
"created_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"report_id": 1, "unique": true},
|
||||
{"report_type": 1},
|
||||
{"generated_date": -1}
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "users",
|
||||
"fields": {
|
||||
"_id": "ObjectId",
|
||||
"user_id": "String",
|
||||
"name": "String",
|
||||
"email": "String",
|
||||
"password_hash": "String",
|
||||
"role": "String",
|
||||
"permissions": "Array",
|
||||
"created_at": "Date"
|
||||
},
|
||||
"indexes": [
|
||||
{"user_id": 1, "unique": true},
|
||||
{"email": 1, "unique": true},
|
||||
{"role": 1}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|finetune_right_pad_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
||||
size 17209920
|
||||
2067
tokenizer_config.json
Normal file
2067
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
3
unsloth.F16.gguf
Normal file
3
unsloth.F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3edeba69fd4d45908900367fdeb485a70b1688d743832e019352fcdff0e12831
|
||||
size 2479595936
|
||||
3
unsloth.Q4_K_M.gguf
Normal file
3
unsloth.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9aac1abfe325ccc396384feb3ffd7cffa1d46c3e8a13702ebb65dc21a8e101cc
|
||||
size 807694752
|
||||
3
unsloth.Q5_K_M.gguf
Normal file
3
unsloth.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7c8ed4d634976b333f3c2a4f4451aa9b93b6bc54c2954ed9505e9aef48d0cf30
|
||||
size 911503776
|
||||
3
unsloth.Q8_0.gguf
Normal file
3
unsloth.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7b5f242dbeb4f645e83c2d4474cc9ff85e2d5141ec5648ae2f1bd64356d8ed8e
|
||||
size 1321083296
|
||||
Reference in New Issue
Block a user