kihyun1998 commited on
Commit
cd62380
Β·
verified Β·
1 Parent(s): cc15fc6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +89 -160
README.md CHANGED
@@ -1,202 +1,131 @@
1
  ---
2
- base_model: unsloth/gemma-2b-bnb-4bit
3
  library_name: peft
 
 
 
 
 
 
 
 
 
4
  ---
 
5
 
6
- # Model Card for Model ID
7
 
8
- <!-- Provide a quick summary of what the model is/does. -->
 
 
9
 
 
10
 
 
11
 
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
-
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
 
 
 
 
 
 
133
 
 
134
 
135
- ## Model Examination [optional]
136
 
137
- <!-- Relevant interpretability work for the model goes here -->
 
 
138
 
139
- [More Information Needed]
 
140
 
141
- ## Environmental Impact
142
 
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
 
144
 
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
 
 
 
 
 
146
 
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
 
153
- ## Technical Specifications [optional]
 
154
 
155
- ### Model Architecture and Objective
 
 
 
156
 
157
- [More Information Needed]
158
 
159
- ### Compute Infrastructure
160
 
161
- [More Information Needed]
 
 
162
 
163
- #### Hardware
164
 
165
- [More Information Needed]
166
 
167
- #### Software
 
 
168
 
169
- [More Information Needed]
170
 
171
- ## Citation [optional]
 
172
 
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
 
175
- **BibTeX:**
176
 
177
- [More Information Needed]
 
 
 
178
 
179
- **APA:**
180
 
181
- [More Information Needed]
182
 
183
- ## Glossary [optional]
 
 
184
 
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
 
187
- [More Information Needed]
188
 
189
- ## More Information [optional]
 
190
 
191
- [More Information Needed]
192
 
193
- ## Model Card Authors [optional]
194
 
195
- [More Information Needed]
 
196
 
197
- ## Model Card Contact
198
 
199
- [More Information Needed]
200
- ### Framework versions
201
 
202
- - PEFT 0.14.0
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: unsloth/gemma-2b-it
3
  library_name: peft
4
+ tags:
5
+ - text-to-mongodb
6
+ - LoRA
7
+ - instruction-tuning
8
+ - mongodb
9
+ - gemma
10
+ license: mit
11
+ language:
12
+ - en
13
  ---
14
+ # 🧠 Gemma 2B - MongoDB Query Generator (LoRA)
15
 
16
+ This is a LoRA fine-tuned version of `unsloth/gemma-2b-it` that converts natural language instructions into **MongoDB query strings** like:
17
 
18
+ ```js
19
+ db.users.find({ "isActive": true, "age": { "$gt": 30 } })
20
+ ```
21
 
22
+ The model is instruction-tuned to support a text-to-query use case for MongoDB across typical collections like `users`, `orders`, and `products`.
23
 
24
+ ---
25
 
26
+ ## ✨ Model Details
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
 
28
+ - **Base model**: [`unsloth/gemma-2b-it`](https://huggingface.co/unsloth/gemma-2b-it)
29
+ - **Fine-tuned with**: LoRA (4-bit quantized)
30
+ - **Framework**: [Unsloth](https://github.com/unslothai/unsloth) + PEFT
31
+ - **Dataset**: Synthetic instructions paired with MongoDB queries (300+ examples)
32
+ - **Use case**: Text-to-MongoDB query generation
33
 
34
+ ---
35
 
36
+ ## πŸ“¦ How to Use
37
 
38
+ ```python
39
+ from peft import PeftModel
40
+ from transformers import AutoTokenizer, AutoModelForCausalLM
41
 
42
+ base = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2b-it", load_in_4bit=True, device_map="auto")
43
+ tokenizer = AutoTokenizer.from_pretrained("unsloth/gemma-2b-it")
44
 
45
+ model = PeftModel.from_pretrained(base, "kihyun1998/gemma-2b-mongodb-lora")
46
 
47
+ prompt = """### Instruction:
48
+ Convert to MongoDB query string.
49
 
50
+ ### Input:
51
+ Collection: users
52
+ Fields:
53
+ - name (string)
54
+ - age (int)
55
+ - isActive (boolean)
56
+ - country (string)
57
 
58
+ Question: Show all active users from Korea older than 30.
 
 
 
 
59
 
60
+ ### Response:
61
+ """
62
 
63
+ inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
64
+ output = model.generate(**inputs, max_new_tokens=100)
65
+ print(tokenizer.decode(output[0], skip_special_tokens=True))
66
+ ```
67
 
68
+ ---
69
 
70
+ ## πŸ’‘ Example Output
71
 
72
+ ```js
73
+ db.users.find({ "isActive": true, "country": "Korea", "age": { "$gt": 30 } })
74
+ ```
75
 
76
+ ---
77
 
78
+ ## πŸ“š Intended Use
79
 
80
+ - Converting business-friendly questions into executable MongoDB queries
81
+ - Powering internal dashboards, query builders, or no-code tools
82
+ - Works best on structured fields and simple query logic
83
 
84
+ ### Out-of-scope:
85
 
86
+ - Complex joins or aggregation pipelines
87
+ - Nested or dynamic schema reasoning
88
 
89
+ ---
90
 
91
+ ## πŸ“Š Training Details
92
 
93
+ - LoRA rank: 16
94
+ - Epochs: 3
95
+ - Dataset: 300+ synthetic natural language β†’ MongoDB query pairs
96
+ - Training hardware: Google Colab (T4 GPU)
97
 
98
+ ---
99
 
100
+ ## 🚧 Limitations
101
 
102
+ - Model assumes collection and fields are already known (RAG context required)
103
+ - May hallucinate field names not present in context
104
+ - Limited handling of advanced MongoDB features like `$lookup`, `$aggregate`
105
 
106
+ ---
107
 
108
+ ## 🧾 License
109
 
110
+ The base model is under [Gemma license](https://ai.google.dev/gemma#license).
111
+ This LoRA adapter inherits the same conditions.
112
 
113
+ ---
114
 
115
+ ## πŸ§‘β€πŸ’» Author
116
 
117
+ - 🐱 [@kihyun1998](https://huggingface.co/kihyun1998)
118
+ - πŸ’¬ Questions? Open an issue or contact via Hugging Face.
119
 
120
+ ---
121
 
122
+ ## 🏁 Citation
 
123
 
124
+ ```bibtex
125
+ @misc{kihyun2025mongodb,
126
+ title={Gemma 2B MongoDB Query Generator (LoRA)},
127
+ author={Kihyun Lee},
128
+ year={2025},
129
+ howpublished={\\url{https://huggingface.co/kihyun1998/gemma-2b-mongodb-lora}}
130
+ }
131
+ ```