Update README.md
Browse files
README.md
CHANGED
|
@@ -5,12 +5,8 @@ base_model:
|
|
| 5 |
- google/gemma-2-9b-it
|
| 6 |
---
|
| 7 |
|
| 8 |
-
# Model Card for Model ID
|
| 9 |
-
|
| 10 |
-
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
|
| 11 |
-
|
| 12 |
## Model Details
|
| 13 |
-
This is gguf format model for neo4j/text2cypher-gemma-2-9b-it-finetuned-2024v1
|
| 14 |
|
| 15 |
### Model Description
|
| 16 |
This model serves as a demonstration of how fine-tuning foundational models using the Neo4j-Text2Cypher(2024) Dataset (https://huggingface.co/datasets/neo4j/text2cypher-2024v1) can enhance performance on the Text2Cypher task.
|
|
@@ -100,7 +96,7 @@ The datasets used were gathered from publicly available sources. Over time, foun
|
|
| 100 |
## Training Details
|
| 101 |
Training Procedure
|
| 102 |
Used RunPod with following setup:
|
| 103 |
-
|
| 104 |
1 x A100 PCIe
|
| 105 |
31 vCPU 117 GB RAM
|
| 106 |
runpod/pytorch:2.4.0-py3.11-cuda12.4.1-devel-ubuntu22.04
|
|
@@ -111,4 +107,4 @@ Training Hyperparameters
|
|
| 111 |
lora_config = LoraConfig( r=64, lora_alpha=64, target_modules=target_modules, lora_dropout=0.05, bias="none", task_type="CAUSAL_LM", )
|
| 112 |
sft_config = SFTConfig( dataset_text_field=dataset_text_field, per_device_train_batch_size=4, gradient_accumulation_steps=8, dataset_num_proc=16, max_seq_length=1600, logging_dir="./logs", num_train_epochs=1, learning_rate=2e-5, save_steps=5, save_total_limit=1, logging_steps=5, output_dir="outputs", optim="paged_adamw_8bit", save_strategy="steps", )
|
| 113 |
bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16, )
|
| 114 |
-
|
|
|
|
| 5 |
- google/gemma-2-9b-it
|
| 6 |
---
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
## Model Details
|
| 9 |
+
This is gguf format model for ```neo4j/text2cypher-gemma-2-9b-it-finetuned-2024v1```
|
| 10 |
|
| 11 |
### Model Description
|
| 12 |
This model serves as a demonstration of how fine-tuning foundational models using the Neo4j-Text2Cypher(2024) Dataset (https://huggingface.co/datasets/neo4j/text2cypher-2024v1) can enhance performance on the Text2Cypher task.
|
|
|
|
| 96 |
## Training Details
|
| 97 |
Training Procedure
|
| 98 |
Used RunPod with following setup:
|
| 99 |
+
```
|
| 100 |
1 x A100 PCIe
|
| 101 |
31 vCPU 117 GB RAM
|
| 102 |
runpod/pytorch:2.4.0-py3.11-cuda12.4.1-devel-ubuntu22.04
|
|
|
|
| 107 |
lora_config = LoraConfig( r=64, lora_alpha=64, target_modules=target_modules, lora_dropout=0.05, bias="none", task_type="CAUSAL_LM", )
|
| 108 |
sft_config = SFTConfig( dataset_text_field=dataset_text_field, per_device_train_batch_size=4, gradient_accumulation_steps=8, dataset_num_proc=16, max_seq_length=1600, logging_dir="./logs", num_train_epochs=1, learning_rate=2e-5, save_steps=5, save_total_limit=1, logging_steps=5, output_dir="outputs", optim="paged_adamw_8bit", save_strategy="steps", )
|
| 109 |
bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16, )
|
| 110 |
+
```
|