reaperdoesntknow commited on
Commit
d52efc7
·
verified ·
1 Parent(s): 230f15b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -6
README.md CHANGED
@@ -19,12 +19,15 @@ pipeline_tag: text-generation
19
 
20
  ---
21
  # Model Card for Qemma-GEI
22
- **Gap Envelope Integral** My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions.
23
- **Redux** This Model underwent an additional merge between Qemma-redux and Qwen3-0.6B, in addition to adding Rope Scaling.
24
- ***Additionally*** Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment.
25
- **Qemma** is a HuggingFace-native hybrid model that merges **Gemma-3 (1B)** and **Qwen-3 (0.6B)** at the weight level (no adapters).
26
- Design: Gemma MLP/body + Qwen attention/head, projected and aligned to Gemma’s hidden size. The model is then SFT-tuned for stepwise reasoning.
27
- This variant uses Yarn based Rope Scaling with 1:1 Ratio from max_position_embeddings
 
 
 
28
  ## Quick start
29
 
30
  ```python
 
19
 
20
  ---
21
  # Model Card for Qemma-GEI
22
+ ## Gap Envelope Integral
23
+ * My mathematical formulation to utilize space projections to "measure" the Jump between points of discontinuity found in Non-Differentialable Functions.
24
+ ## Redux
25
+ * This Model underwent an additional merge between Qemma-redux and Qwen3-0.6B, in addition to adding Rope Scaling.
26
+ ### Additionally
27
+ * Fusion Logic was updated to aid per layer fusion and post fusion embedding alignment.
28
+ * **Qemma** is a HuggingFace-native hybrid model that merges **Gemma-3 (1B)** and **Qwen-3 (0.6B)** at the weight level (no adapters).
29
+ * Design: Gemma MLP/body + Qwen attention/head, projected and aligned to Gemma’s hidden size. The model is then SFT-tuned for stepwise reasoning.
30
+ * This variant uses Yarn based Rope Scaling with 1:1 Ratio from max_position_embeddings
31
  ## Quick start
32
 
33
  ```python