Update README.md
#5
by
hypothetical
- opened
README.md
CHANGED
|
@@ -5,7 +5,7 @@ base_model:
|
|
| 5 |
pipeline_tag: text2text-generation
|
| 6 |
---
|
| 7 |
|
| 8 |
-
# Elastic models
|
| 9 |
|
| 10 |
Elastic models are the models produced by TheStage AI ANNA: Automated Neural Networks Accelerator. ANNA allows you to control model size, latency and quality with a simple slider movement. For each model, ANNA produces a series of optimized models:
|
| 11 |
|
|
@@ -28,6 +28,9 @@ __Goals of elastic models:__
|
|
| 28 |
|
| 29 |
> It's important to note that specific quality degradation can vary from model to model. For instance, with an S model, you can have 0.5% degradation as well.
|
| 30 |
|
|
|
|
|
|
|
|
|
|
| 31 |
-----
|
| 32 |
|
| 33 |
## Inference
|
|
|
|
| 5 |
pipeline_tag: text2text-generation
|
| 6 |
---
|
| 7 |
|
| 8 |
+
# Elastic model: Mistral-7B-Instruct-v0.3. Fastest and most flexible models for self-serving.
|
| 9 |
|
| 10 |
Elastic models are the models produced by TheStage AI ANNA: Automated Neural Networks Accelerator. ANNA allows you to control model size, latency and quality with a simple slider movement. For each model, ANNA produces a series of optimized models:
|
| 11 |
|
|
|
|
| 28 |
|
| 29 |
> It's important to note that specific quality degradation can vary from model to model. For instance, with an S model, you can have 0.5% degradation as well.
|
| 30 |
|
| 31 |
+
|
| 32 |
+

|
| 33 |
+
|
| 34 |
-----
|
| 35 |
|
| 36 |
## Inference
|