GODELEV commited on
Commit
0f6d1b9
·
verified ·
1 Parent(s): 00aa281

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  license: apache-2.0
3
- base_model: HuggingFaceTB/SmolLM3-3B-Instruct
 
4
  tags:
5
  - trl
6
  - unsloth
@@ -9,11 +10,13 @@ tags:
9
  - transformers
10
  library_name: transformers
11
  model_name: Generator3B-V0.1
 
 
12
  ---
13
 
14
  # Generator3B-V0.1
15
 
16
- This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Instruct).
17
  It was trained using **Unsloth** and the **SFTTrainer** on a specialized 'Golden Dataset' for high-quality instruction following.
18
 
19
  ## Model Details
@@ -28,4 +31,4 @@ The model was trained with maximum speed optimizations including:
28
  - **Sequence Packing**: Enabled
29
  - **4-bit Quantization**: Bitsandbytes
30
  - **LoRA Rank**: 64
31
- - **Optimizers**: AdamW 8-bit
 
1
  ---
2
  license: apache-2.0
3
+ base_model:
4
+ - HuggingFaceTB/SmolLM3-3B
5
  tags:
6
  - trl
7
  - unsloth
 
10
  - transformers
11
  library_name: transformers
12
  model_name: Generator3B-V0.1
13
+ datasets:
14
+ - GODELEV/Golden-Dataset-Beta3
15
  ---
16
 
17
  # Generator3B-V0.1
18
 
19
+ This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B).
20
  It was trained using **Unsloth** and the **SFTTrainer** on a specialized 'Golden Dataset' for high-quality instruction following.
21
 
22
  ## Model Details
 
31
  - **Sequence Packing**: Enabled
32
  - **4-bit Quantization**: Bitsandbytes
33
  - **LoRA Rank**: 64
34
+ - **Optimizers**: AdamW 8-bit