stablelm-tuned-alpha-3b


Find this model in the StableLM model summary

Model source: https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b

stablelm-tuned-alpha-3b Model Summary Plots

stablelm-tuned-alpha-3b Model Selected Details
  layer_type N M Q alpha D alpha-hat log_SN rank_loss
layer_id                  
4 DENSE 12288 4096 3.00 3.28 0.02 7.47 2.28 0
5 DENSE 4096 4096 1.00 3.44 0.03 5.69 1.65 7
6 DENSE 16384 4096 4.00 6.87 0.06 13.38 1.95 0
7 DENSE 16384 4096 4.00 7.54 0.06 19.37 2.57 0
10 DENSE 12288 4096 3.00 3.57 0.01 7.16 2.01 0
11 DENSE 4096 4096 1.00 5.61 0.03 7.10 1.27 4
12 DENSE 16384 4096 4.00 3.39 0.03 7.69 2.27 0
13 DENSE 16384 4096 4.00 5.92 0.03 11.81 2.00 0
16 DENSE 12288 4096 3.00 3.40 0.02 6.15 1.81 0
17 DENSE 4096 4096 1.00 4.07 0.02 6.29 1.55 5
18 DENSE 16384 4096 4.00 2.99 0.01 6.47 2.16 0
19 DENSE 16384 4096 4.00 3.28 0.03 6.31 1.93 0
22 DENSE 12288 4096 3.00 4.13 0.02 7.60 1.84 0
23 DENSE 4096 4096 1.00 3.56 0.04 5.81 1.63 4
24 DENSE 16384 4096 4.00 3.22 0.01 6.97 2.16 0
25 DENSE 16384 4096 4.00 4.05 0.02 7.77 1.92 0
28 DENSE 12288 4096 3.00 3.45 0.01 6.57 1.91 0
29 DENSE 4096 4096 1.00 4.60 0.05 7.54 1.64 4
30 DENSE 16384 4096 4.00 3.37 0.01 7.52 2.23 0
31 DENSE 16384 4096 4.00 3.65 0.03 6.75 1.85 0
34 DENSE 12288 4096 3.00 3.16 0.02 6.43 2.03 0
35 DENSE 4096 4096 1.00 2.81 0.05 5.06 1.80 4
36 DENSE 16384 4096 4.00 3.42 0.01 7.62 2.23 0
37 DENSE 16384 4096 4.00 3.83 0.02 7.17 1.87 0
40 DENSE 12288 4096 3.00 3.42 0.01 7.45 2.18 0
41 DENSE 4096 4096 1.00 3.28 0.04 6.04 1.84 5
42 DENSE 16384 4096 4.00 3.41 0.01 7.58 2.22 0
43 DENSE 16384 4096 4.00 3.75 0.02 7.10 1.89 0
46 DENSE 12288 4096 3.00 4.02 0.02 8.79 2.18 0
47 DENSE 4096 4096 1.00 2.89 0.04 5.51 1.90 4
48 DENSE 16384 4096 4.00 3.42 0.01 7.40 2.16 0
49 DENSE 16384 4096 4.00 3.98 0.02 7.41 1.86 0
52 DENSE 12288 4096 3.00 4.06 0.03 9.38 2.31 0
53 DENSE 4096 4096 1.00 5.32 0.06 8.08 1.52 4
54 DENSE 16384 4096 4.00 3.43 0.01 7.29 2.12 0
55 DENSE 16384 4096 4.00 4.38 0.02 7.34 1.68 0
58 DENSE 12288 4096 3.00 3.40 0.02 8.60 2.53 0
59 DENSE 4096 4096 1.00 3.22 0.05 4.08 1.27 4
60 DENSE 16384 4096 4.00 3.46 0.01 7.00 2.02 0
61 DENSE 16384 4096 4.00 6.28 0.01 9.49 1.51 0
64 DENSE 12288 4096 3.00 3.20 0.02 8.56 2.68 0
65 DENSE 4096 4096 1.00 7.57 0.08 9.14 1.21 4
66 DENSE 16384 4096 4.00 3.45 0.01 6.96 2.02 0
67 DENSE 16384 4096 4.00 5.38 0.01 7.76 1.44 0
70 DENSE 12288 4096 3.00 3.15 0.04 8.68 2.76 0
71 DENSE 4096 4096 1.00 3.19 0.09 3.93 1.23 4
73 DENSE 16384 4096 4.00 3.50 0.01 6.93 1.98 0
74 DENSE 16384 4096 4.00 6.11 0.01 8.14 1.33 0
77 DENSE 12288 4096 3.00 2.21 0.03 6.45 2.92 0
78 DENSE 4096 4096 1.00 9.48 0.07 8.25 0.87 4
79 DENSE 16384 4096 4.00 3.53 0.01 6.79 1.92 0
80 DENSE 16384 4096 4.00 5.99 0.01 7.58 1.26 0
83 DENSE 12288 4096 3.00 2.18 0.03 6.38 2.93 0
84 DENSE 4096 4096 1.00 11.20 0.04 6.69 0.60 4
85 DENSE 16384 4096 4.00 3.65 0.01 6.89 1.89 0
86 DENSE 16384 4096 4.00 5.59 0.02 7.30 1.31 0
89 DENSE 12288 4096 3.00 2.82 0.04 8.53 3.02 0
90 DENSE 4096 4096 1.00 5.93 0.04 8.02 1.35 3
91 DENSE 16384 4096 4.00 3.77 0.01 7.27 1.93 0
92 DENSE 16384 4096 4.00 4.84 0.03 6.83 1.41 0
95 DENSE 12288 4096 3.00 1.98 0.05 5.87 2.97 0
96 DENSE 4096 4096 1.00 4.12 0.07 8.57 2.08 5
97 DENSE 16384 4096 4.00 3.92 0.02 8.06 2.05 0
98 DENSE 16384 4096 4.00 3.33 0.01 7.36 2.21 0