Files changed (1) hide show
  1. README.md +32 -2
README.md CHANGED
@@ -10,16 +10,46 @@ base_model:
10
  - yam-peleg/Experiment28-7B
11
  ---
12
 
13
- # YamshadowExperiment28-7B
14
 
15
  YamshadowExperiment28-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
16
  * [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B)
17
  * [yam-peleg/Experiment28-7B](https://huggingface.co/yam-peleg/Experiment28-7B)
18
 
19
- **YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24). I don't recommend using it because of issues that are not reflected in the benchmarks.**
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
 
21
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/ONmehD2GXYefb-O3zHbp5.png)
22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  ## 🧩 Configuration
24
 
25
  ```yaml
 
10
  - yam-peleg/Experiment28-7B
11
  ---
12
 
13
+ # 🧪 YamshadowExperiment28-7B
14
 
15
  YamshadowExperiment28-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
16
  * [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B)
17
  * [yam-peleg/Experiment28-7B](https://huggingface.co/yam-peleg/Experiment28-7B)
18
 
19
+ ## 🔍 Applications
20
+
21
+ This model uses a context window of 8k. I recommend using it with the Alpaca chat template (works perfectly with LM Studio).
22
+
23
+ The model can sometimes break and output a lot of "INST". From my experience, its excellent results on the Open LLM Leaderboard are probably a sign of overfitting.
24
+
25
+ ## ⚡ Quantized models
26
+
27
+ * **GGUF**: https://huggingface.co/automerger/YamshadowExperiment28-7B-GGUF
28
+
29
+ ## 🏆 Evaluation
30
+
31
+ ### Open LLM Leaderboard
32
+
33
+ YamshadowExperiment28-7B is currently the best-performing 7B model on the Open LLM Leaderboard (08 Apr 24).
34
 
35
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/ONmehD2GXYefb-O3zHbp5.png)
36
 
37
+ ### EQ-bench
38
+
39
+ Thanks to [Samuel J. Paech](https://twitter.com/sam_paech), who kindly ran the evaluation.
40
+
41
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/e6cg_7TD35JveTjx_KoTT.png)
42
+
43
+ ### Nous
44
+
45
+ Evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval). See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
46
+
47
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/s4oKdK3FfaDsagXe7tEM2.png)
48
+
49
+ ## 🌳 Model Family Tree
50
+
51
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/fEA4EdtSa_fssdvsUXPf1.png)
52
+
53
  ## 🧩 Configuration
54
 
55
  ```yaml