Update README.md
Browse files
README.md
CHANGED
@@ -82,8 +82,15 @@ If you wish to use the original data, please contact the original author directl
|
|
82 |
|
83 |
|
84 |
## Training Details
|
85 |
-
|
86 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
|
88 |
|
89 |
### Training Data
|
@@ -95,15 +102,15 @@ If you wish to use the original data, please contact the original author directl
|
|
95 |
5. μ€μλ²€μ²κΈ°μ
λΆ/λνλ―Όκ΅μ λΆ: μ€μλ²€μ²κΈ°μ
λΆ μ λ¬Έμ©μ΄(<https://terms.naver.com/list.naver?cid=42103&categoryId=42103>)
|
96 |
6. κ³ μ±μΌ/λ²λ¬ΈμΆνμ¬: νκ³Β·μΈλ¬΄ μ©μ΄μ¬μ (<https://terms.naver.com/list.naver?cid=51737&categoryId=51737>)
|
97 |
7. 맨νμ κ²½μ ν 8ν Word Index
|
98 |
-
8.
|
99 |
|
100 |
|
101 |
-
|
102 |
|
103 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
104 |
|
105 |
|
106 |
-
|
|
|
107 |
|
108 |
|Hyperparameter|SGEcon/KoSOLAR-10.7B-v0.2_fin_v4|
|
109 |
|------|---|
|
@@ -116,26 +123,12 @@ If you wish to use the original data, please contact the original author directl
|
|
116 |
|lora dropout|0.05|
|
117 |
|optim|paged_adamw_32bit|
|
118 |
|target_modules|q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, lm_head|
|
119 |
-
|
120 |
-
## Evaluation
|
121 |
-
|
122 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
123 |
|
124 |
-
|
125 |
-
|
126 |
-
#### Testing Data
|
127 |
-
|
128 |
-
<!-- This should link to a Dataset Card if possible. -->
|
129 |
-
|
130 |
-
[More Information Needed]
|
131 |
-
|
132 |
-
### Results
|
133 |
-
|
134 |
-
[More Information Needed]
|
135 |
|
136 |
-
|
137 |
|
|
|
138 |
|
139 |
-
|
140 |
|
141 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
|
|
82 |
|
83 |
|
84 |
## Training Details
|
85 |
+
|
86 |
+
We use QLora to train the base model.
|
87 |
+
Quantized Low Rank Adapters (QLoRA) is an efficient technique that uses 4-bit quantized pre-trained language models to fine-tune 65 billion parameter models on a 48 GB GPU while significantly reducing memory usage.
|
88 |
+
The method uses NormalFloat 4-bit (NF4), a new data type that is theoretically optimal for normally distributed weights; Double Quantization, which further quantizes quantization constants to reduce average memory usage; and Paged Optimizers, which manage memory spikes during mini-batch processing, to increase memory efficiency without sacrificing performance.
|
89 |
+
|
90 |
+
Also, we performed instruction tuning using the data that we collected and the kyujinpy/KOR-OpenOrca-Platypus-v3 dataset on the hugging face.
|
91 |
+
Instruction tuning is learning in a supervised learning format that uses instructions and input data together as input and output data as a pair.
|
92 |
+
|
93 |
+
|
94 |
|
95 |
|
96 |
### Training Data
|
|
|
102 |
5. μ€μλ²€μ²κΈ°μ
λΆ/λνλ―Όκ΅μ λΆ: μ€μλ²€μ²κΈ°μ
λΆ μ λ¬Έμ©μ΄(<https://terms.naver.com/list.naver?cid=42103&categoryId=42103>)
|
103 |
6. κ³ μ±μΌ/λ²λ¬ΈμΆνμ¬: νκ³Β·μΈλ¬΄ μ©μ΄μ¬μ (<https://terms.naver.com/list.naver?cid=51737&categoryId=51737>)
|
104 |
7. 맨νμ κ²½μ ν 8ν Word Index
|
105 |
+
8. kyujinpy/KOR-OpenOrca-Platypus-v3(<https://huggingface.co/datasets/kyujinpy/KOR-OpenOrca-Platypus-v3>)
|
106 |
|
107 |
|
108 |
+
The copyright of the data used belongs to the original author, so please contact the original author when using it.
|
109 |
|
|
|
110 |
|
111 |
|
112 |
+
|
113 |
+
### Training Hyperparameters
|
114 |
|
115 |
|Hyperparameter|SGEcon/KoSOLAR-10.7B-v0.2_fin_v4|
|
116 |
|------|---|
|
|
|
123 |
|lora dropout|0.05|
|
124 |
|optim|paged_adamw_32bit|
|
125 |
|target_modules|q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, lm_head|
|
|
|
|
|
|
|
|
|
126 |
|
127 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
|
129 |
+
### Example
|
130 |
|
131 |
+
> μ€μμνμ μν μ λν΄μ μ€λͺ
ν΄μ€λ?
|
132 |
|
133 |
+
>> μ€μμνμ ν΅νλ°νκΆκ³Ό κΈμ΅ν΅μ κΆμ κ°μ§ κΈ°κ΄μ΄λ€. μ€μμνμ κ΅κ°μ ν΅νμ μ±
, μΈνμ μ±
, κΈμ΅μ μ±
μ μ립νλ λμμ μμ
μνκ³Ό κ°μ κΈμ΅κΈ°κ΄μ κ°λ
Β·κ°λ
νλ μ
무λ₯Ό μννλ€. μ€μμνμ μ λΆμ μμ
μνμ λν μκΈλλΆκΈ°κ΄μ΄λ€. μμ
μνμ μ€μμνμ μκΈμ λΉλ¦¬κ±°λ μκΈνλ€. μ€μμνμ ν΅νμ μ©μ μ±
μ μννκΈ° μν΄ κΈμ΅κΈ°κ΄μ ν΅ν΄ μκΈμ λμΆνκ±°λ μκΈ λ°λλ€. μ€μμνμ μμ
μνμ λν μκΈλλΆκΈ°κ΄μ μν κ³Ό ν¨κ» μμ€μνμ λν κ°λ
Β·κ°λ
μ μν μ μννλ€. μμ
μνμ΄ μκΈμ λμΆν λλ 1μ°¨μ μΌλ‘ μμ
μνμ λμΆκΈμ μ§κΈνλ λμ , λμΆμνμ λμΆκΈμ μΌλΆ λλ μ μ‘μ μκΈμΌλ‘ λ°μ μ€μμνμ λμ λΉλ €μ£Όκ³ μκΈνλ€. μκΈμ λν μ΄μμ¨μ λμ¬ μκΈμκ° μ€μμνμ μκΈμ νκ²λ μ λνλ κ²μ΄λ€. ννΈ μμ
μνμ λμΆμ ν λ λμΆμνμ΄ λμΆκΈμ μκΈνλ λμ , λμΆμ λ°λ μνμ λμΆκΈμ μ§κΈνλ€.
|
134 |
|
|