Commit
•
62d1c2f
1
Parent(s):
9817f85
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,9 @@ language:
|
|
| 6 |
# DeciLM-7B
|
| 7 |
|
| 8 |
DeciLM-7B is a 7.04 billion parameter decoder-only text generation model, released under the Apache 2.0 license. At the time of release, DeciLM-7B is the top-performing 7B base language model on the Open LLM Leaderboard. With support for an 8K-token sequence length, this highly efficient model uses variable Grouped-Query Attention (GQA) to achieve a superior balance between accuracy and computational efficiency. The model's architecture was generated using Deci's proprietary Neural Architecture Search technology, AutoNAC.
|
|
|
|
|
|
|
|
|
|
| 9 |
## Model Details
|
| 10 |
|
| 11 |
### Model Description
|
|
@@ -65,8 +68,6 @@ Below are DeciLM-7B and DeciLM-7B-instruct's Open LLM Leaderboard results.
|
|
| 65 |
| DecilLM-7B | 61.55 | 59.39 | 82.51 | 59.76 | 40.33 | 79.95 | 47.38 |
|
| 66 |
| DecilLM-7B-instruct | 63.19 | 61.01 | 82.37 | 60.24 | 49.75 | 79.72 | 46.02 |
|
| 67 |
|
| 68 |
-
|
| 69 |
-
|
| 70 |
### Runtime Benchmarks
|
| 71 |
|
| 72 |
| Inference Tool | Hardware | Prompt length | Generation length | Generated tokens/sec | Batch Size | Number of Prompts |
|
|
|
|
| 6 |
# DeciLM-7B
|
| 7 |
|
| 8 |
DeciLM-7B is a 7.04 billion parameter decoder-only text generation model, released under the Apache 2.0 license. At the time of release, DeciLM-7B is the top-performing 7B base language model on the Open LLM Leaderboard. With support for an 8K-token sequence length, this highly efficient model uses variable Grouped-Query Attention (GQA) to achieve a superior balance between accuracy and computational efficiency. The model's architecture was generated using Deci's proprietary Neural Architecture Search technology, AutoNAC.
|
| 9 |
+
|
| 10 |
+
### 🔥 Click [here](https://console.deci.ai/infery-llm-demo) for a live demo of DeciLM-7B + Infery!
|
| 11 |
+
|
| 12 |
## Model Details
|
| 13 |
|
| 14 |
### Model Description
|
|
|
|
| 68 |
| DecilLM-7B | 61.55 | 59.39 | 82.51 | 59.76 | 40.33 | 79.95 | 47.38 |
|
| 69 |
| DecilLM-7B-instruct | 63.19 | 61.01 | 82.37 | 60.24 | 49.75 | 79.72 | 46.02 |
|
| 70 |
|
|
|
|
|
|
|
| 71 |
### Runtime Benchmarks
|
| 72 |
|
| 73 |
| Inference Tool | Hardware | Prompt length | Generation length | Generated tokens/sec | Batch Size | Number of Prompts |
|