Text Generation
MLX
Safetensors
qwen3
programming
code generation
code
codeqwen
Mixture of Experts
coding
coder
qwen2
chat
qwen
qwen-coder
finetune
brainstorm 20x
brainstorm
optional thinking
creative
all use cases
QiMing
QiMing-holos
bagua
decision-making
strategic-analysis
cognitive-architecture
philosophy-driven-ai
conversational
6-bit
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,9 @@ pipeline_tag: text-generation
|
|
| 41 |
|
| 42 |
Metrics from this model are still being generated, and since this is a local process it will take some time.
|
| 43 |
|
| 44 |
-
Here are however metrics from the 21B q5-hi model, compared to the QiMing baseline in BF16
|
|
|
|
|
|
|
| 45 |
|
| 46 |
QiMing Model Performance Analysis: New Base Model Benchmarks
|
| 47 |
|
|
|
|
| 41 |
|
| 42 |
Metrics from this model are still being generated, and since this is a local process it will take some time.
|
| 43 |
|
| 44 |
+
Here are however metrics from the 21B q5-hi model, compared to the QiMing baseline in BF16, to show how brainstorming affects this model
|
| 45 |
+
|
| 46 |
+
The 17B has less brainstorming applied.
|
| 47 |
|
| 48 |
QiMing Model Performance Analysis: New Base Model Benchmarks
|
| 49 |
|