Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,8 @@ license: mit
|
|
| 13 |
|
| 14 |
## Model Description
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of `
|
|
|
|
| 17 |
|
| 18 |
### Supported Tasks
|
| 19 |
|
|
@@ -29,13 +30,6 @@ This model is a fine-tuned version of `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`,
|
|
| 29 |
|
| 30 |
The model is fine-tuned on specialized crypto and web3 prompts. Training data should be placed in the `./json/` directory in JSONL format.
|
| 31 |
|
| 32 |
-
## Technical Specifications
|
| 33 |
-
|
| 34 |
-
- **Base Model**: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
| 35 |
-
- **Training Type**: Supervised Fine-Tuning (SFT)
|
| 36 |
-
- **Required Python Version**: 3.13+
|
| 37 |
-
- **Package Manager**: uv
|
| 38 |
-
|
| 39 |
## Performance and Limitations
|
| 40 |
|
| 41 |
The model is optimized for:
|
|
|
|
| 13 |
|
| 14 |
## Model Description
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of `Qwen-7B`, specifically optimized for cryptocurrency, Web3, and DeFi-related tasks.
|
| 17 |
+
It is designed to provide specialized knowledge and decision ability while maintaining computational efficiency.
|
| 18 |
|
| 19 |
### Supported Tasks
|
| 20 |
|
|
|
|
| 30 |
|
| 31 |
The model is fine-tuned on specialized crypto and web3 prompts. Training data should be placed in the `./json/` directory in JSONL format.
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
## Performance and Limitations
|
| 34 |
|
| 35 |
The model is optimized for:
|