Commit ·
8b9e3bf
1
Parent(s): 3746711
updated read me
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ tags:
|
|
| 22 |
**Languages:** English
|
| 23 |
**License:** Apache 2.0
|
| 24 |
|
| 25 |
-
This model is a LoRA-finetuned version of **LLaMA2**, adapted for **technology-related conversational tasks**. It supports safe and efficient text generation while keeping the base model frozen and training only LoRA adapters.
|
| 26 |
|
| 27 |
---
|
| 28 |
|
|
@@ -32,7 +32,7 @@ This model is a LoRA-finetuned version of **LLaMA2**, adapted for **technology-r
|
|
| 32 |
This model is intended for **technology-related text generation**, conversational tasks, and research purposes. It was trained using LoRA adapters on technology domain datasets and is compatible with Hugging Face Transformers for inference.
|
| 33 |
|
| 34 |
- **LoRA adapters:** Low-rank adaptation for efficient fine-tuning
|
| 35 |
-
- **Base model:** LLaMA2
|
| 36 |
- **Model weights format:** Safetensors
|
| 37 |
- **Intended use:** Research, simulation, conversational AI for technology domain
|
| 38 |
|
|
|
|
| 22 |
**Languages:** English
|
| 23 |
**License:** Apache 2.0
|
| 24 |
|
| 25 |
+
This model is a LoRA-finetuned version of **LLaMA2 7B**, adapted for **technology-related conversational tasks**. It supports safe and efficient text generation while keeping the base model frozen and training only LoRA adapters.
|
| 26 |
|
| 27 |
---
|
| 28 |
|
|
|
|
| 32 |
This model is intended for **technology-related text generation**, conversational tasks, and research purposes. It was trained using LoRA adapters on technology domain datasets and is compatible with Hugging Face Transformers for inference.
|
| 33 |
|
| 34 |
- **LoRA adapters:** Low-rank adaptation for efficient fine-tuning
|
| 35 |
+
- **Base model:** LLaMA2 7B
|
| 36 |
- **Model weights format:** Safetensors
|
| 37 |
- **Intended use:** Research, simulation, conversational AI for technology domain
|
| 38 |
|