Update README.md
Browse files
README.md
CHANGED
|
@@ -4,11 +4,157 @@ base_model:
|
|
| 4 |
- neuronpedia/jacobian-lens
|
| 5 |
---
|
| 6 |
|
| 7 |
-
|
| 8 |
|
| 9 |
-
|
| 10 |
|
|
|
|
| 11 |
Qwen-2.5-7b-Instruct
|
| 12 |
|
|
|
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- neuronpedia/jacobian-lens
|
| 5 |
---
|
| 6 |
|
| 7 |
+
GGUF conversion of neuronpedia/jacobian-lens
|
| 8 |
|
| 9 |
+
Requires patches to work with llama.cpp
|
| 10 |
|
| 11 |
+
# Manually Tested / verified identical predictions
|
| 12 |
Qwen-2.5-7b-Instruct
|
| 13 |
|
| 14 |
+
# Converted Models
|
| 15 |
|
| 16 |
+
```
|
| 17 |
+
#gemma-2-27b
|
| 18 |
+
d_model=4608 n_prompts=780 layers=0..44 (45) dtype=f16
|
| 19 |
+
gguf: jacobian-lens-GGUF/gemma-2-27b-jlens.gguf
|
| 20 |
|
| 21 |
+
#gemma-2-2b
|
| 22 |
+
d_model=2304 n_prompts=454 layers=0..24 (25) dtype=f16
|
| 23 |
+
gguf: jacobian-lens-GGUF/gemma-2-2b-jlens.gguf
|
| 24 |
+
|
| 25 |
+
#gemma-2-2b-it
|
| 26 |
+
d_model=2304 n_prompts=337 layers=0..24 (25) dtype=f16
|
| 27 |
+
gguf: jacobian-lens-GGUF/gemma-2-2b-it-jlens.gguf
|
| 28 |
+
|
| 29 |
+
#gemma-2-9b
|
| 30 |
+
d_model=3584 n_prompts=462 layers=0..40 (41) dtype=f16
|
| 31 |
+
gguf: jacobian-lens-GGUF/gemma-2-9b-jlens.gguf
|
| 32 |
+
|
| 33 |
+
#gemma-2-9b-it
|
| 34 |
+
d_model=3584 n_prompts=453 layers=0..40 (41) dtype=f16
|
| 35 |
+
gguf: jacobian-lens-GGUF/gemma-2-9b-it-jlens.gguf
|
| 36 |
+
|
| 37 |
+
#gemma-3-12b
|
| 38 |
+
d_model=3840 n_prompts=775 layers=0..46 (47) dtype=f16
|
| 39 |
+
gguf: jacobian-lens-GGUF/gemma-3-12b-jlens.gguf
|
| 40 |
+
|
| 41 |
+
#gemma-3-12b-it
|
| 42 |
+
d_model=3840 n_prompts=844 layers=0..46 (47) dtype=f16
|
| 43 |
+
gguf: jacobian-lens-GGUF/gemma-3-12b-it-jlens.gguf
|
| 44 |
+
|
| 45 |
+
#gemma-3-1b
|
| 46 |
+
d_model=1152 n_prompts=467 layers=0..24 (25) dtype=f16
|
| 47 |
+
gguf: jacobian-lens-GGUF/gemma-3-1b-jlens.gguf
|
| 48 |
+
|
| 49 |
+
#gemma-3-1b-it
|
| 50 |
+
d_model=1152 n_prompts=460 layers=0..24 (25) dtype=f16
|
| 51 |
+
gguf: jacobian-lens-GGUF/gemma-3-1b-it-jlens.gguf
|
| 52 |
+
|
| 53 |
+
#gemma-3-270m
|
| 54 |
+
d_model=640 n_prompts=302 layers=0..16 (17) dtype=f16
|
| 55 |
+
gguf: jacobian-lens-GGUF/gemma-3-270m-jlens.gguf
|
| 56 |
+
|
| 57 |
+
#gemma-3-270m-it
|
| 58 |
+
d_model=640 n_prompts=278 layers=0..16 (17) dtype=f16
|
| 59 |
+
gguf: jacobian-lens-GGUF/gemma-3-270m-it-jlens.gguf
|
| 60 |
+
|
| 61 |
+
#gemma-3-27b
|
| 62 |
+
d_model=5376 n_prompts=670 layers=0..60 (61) dtype=f16
|
| 63 |
+
gguf: jacobian-lens-GGUF/gemma-3-27b-jlens.gguf
|
| 64 |
+
|
| 65 |
+
#gemma-3-27b-it
|
| 66 |
+
d_model=5376 n_prompts=828 layers=0..60 (61) dtype=f16
|
| 67 |
+
gguf: jacobian-lens-GGUF/gemma-3-27b-it-jlens.gguf
|
| 68 |
+
|
| 69 |
+
#gemma-3-4b
|
| 70 |
+
d_model=2560 n_prompts=616 layers=0..32 (33) dtype=f16
|
| 71 |
+
gguf: jacobian-lens-GGUF/gemma-3-4b-jlens.gguf
|
| 72 |
+
|
| 73 |
+
#gemma-3-4b-it
|
| 74 |
+
d_model=2560 n_prompts=546 layers=0..32 (33) dtype=f16
|
| 75 |
+
gguf: jacobian-lens-GGUF/gemma-3-4b-it-jlens.gguf
|
| 76 |
+
|
| 77 |
+
#gemma-4-31b
|
| 78 |
+
d_model=5376 n_prompts=861 layers=0..58 (59) dtype=f16
|
| 79 |
+
gguf: jacobian-lens-GGUF/gemma-4-31b-jlens.gguf
|
| 80 |
+
|
| 81 |
+
#gemma-4-e2b
|
| 82 |
+
d_model=1536 n_prompts=455 layers=0..33 (34) dtype=f16
|
| 83 |
+
gguf: jacobian-lens-GGUF/gemma-4-e2b-jlens.gguf
|
| 84 |
+
|
| 85 |
+
#gemma-4-e4b
|
| 86 |
+
d_model=2560 n_prompts=663 layers=0..40 (41) dtype=f16
|
| 87 |
+
gguf: jacobian-lens-GGUF/gemma-4-e4b-jlens.gguf
|
| 88 |
+
|
| 89 |
+
#gpt2-small
|
| 90 |
+
d_model=768 n_prompts=277 layers=0..10 (11) dtype=f16
|
| 91 |
+
gguf: jacobian-lens-GGUF/gpt2-small-jlens.gguf
|
| 92 |
+
|
| 93 |
+
#gpt-oss-20b
|
| 94 |
+
d_model=2880 n_prompts=457 layers=0..22 (23) dtype=f16
|
| 95 |
+
gguf: jacobian-lens-GGUF/gpt-oss-20b-jlens.gguf
|
| 96 |
+
|
| 97 |
+
#llama3.1-8b
|
| 98 |
+
d_model=4096 n_prompts=539 layers=0..30 (31) dtype=f16
|
| 99 |
+
gguf: jacobian-lens-GGUF/llama3.1-8b-jlens.gguf
|
| 100 |
+
|
| 101 |
+
#llama3.1-8b-it
|
| 102 |
+
d_model=4096 n_prompts=461 layers=0..30 (31) dtype=f16
|
| 103 |
+
gguf: jacobian-lens-GGUF/llama3.1-8b-it-jlens.gguf
|
| 104 |
+
|
| 105 |
+
#llama3.3-70b-it
|
| 106 |
+
d_model=8192 n_prompts=125 layers=0..78 (79) dtype=f16
|
| 107 |
+
gguf: jacobian-lens-GGUF/llama3.3-70b-it-jlens.gguf
|
| 108 |
+
|
| 109 |
+
#olmo-3-1025-7b
|
| 110 |
+
d_model=4096 n_prompts=616 layers=0..30 (31) dtype=f16
|
| 111 |
+
gguf: jacobian-lens-GGUF/olmo-3-1025-7b-jlens.gguf
|
| 112 |
+
|
| 113 |
+
#olmo-3-1125-32b
|
| 114 |
+
d_model=5120 n_prompts=470 layers=0..62 (63) dtype=f16
|
| 115 |
+
gguf: jacobian-lens-GGUF/olmo-3-1125-32b-jlens.gguf
|
| 116 |
+
|
| 117 |
+
#qwen2.5-7b-it
|
| 118 |
+
d_model=3584 n_prompts=485 layers=0..26 (27) dtype=f16
|
| 119 |
+
gguf: jacobian-lens-GGUF/qwen2.5-7b-it-jlens.gguf
|
| 120 |
+
|
| 121 |
+
#qwen3-14b
|
| 122 |
+
d_model=5120 n_prompts=615 layers=0..38 (39) dtype=f16
|
| 123 |
+
gguf: jacobian-lens-GGUF/qwen3-14b-jlens.gguf
|
| 124 |
+
|
| 125 |
+
#qwen3-1.7b
|
| 126 |
+
d_model=2048 n_prompts=466 layers=0..26 (27) dtype=f16
|
| 127 |
+
gguf: jacobian-lens-GGUF/qwen3-1.7b-jlens.gguf
|
| 128 |
+
|
| 129 |
+
#qwen3-4b
|
| 130 |
+
d_model=2560 n_prompts=479 layers=0..34 (35) dtype=f16
|
| 131 |
+
gguf: jacobian-lens-GGUF/qwen3-4b-jlens.gguf
|
| 132 |
+
|
| 133 |
+
#qwen3.5-0.8b
|
| 134 |
+
d_model=1024 n_prompts=233 layers=0..22 (23) dtype=f16
|
| 135 |
+
gguf: jacobian-lens-GGUF/qwen3.5-0.8b-jlens.gguf
|
| 136 |
+
|
| 137 |
+
#qwen3.5-27b
|
| 138 |
+
d_model=5120 n_prompts=672 layers=0..62 (63) dtype=f16
|
| 139 |
+
gguf: jacobian-lens-GGUF/qwen3.5-27b-jlens.gguf
|
| 140 |
+
|
| 141 |
+
#qwen3.5-2b-pt
|
| 142 |
+
d_model=2048 n_prompts=335 layers=0..22 (23) dtype=f16
|
| 143 |
+
gguf: jacobian-lens-GGUF/qwen3.5-2b-pt-jlens.gguf
|
| 144 |
+
|
| 145 |
+
#qwen3.5-4b
|
| 146 |
+
d_model=2560 n_prompts=1000 layers=0..30 (31) dtype=f16
|
| 147 |
+
gguf: jacobian-lens-GGUF/qwen3.5-4b-jlens.gguf
|
| 148 |
+
|
| 149 |
+
#qwen3.5-9b-pt
|
| 150 |
+
d_model=4096 n_prompts=458 layers=0..30 (31) dtype=f16
|
| 151 |
+
gguf: jacobian-lens-GGUF/qwen3.5-9b-pt-jlens.gguf
|
| 152 |
+
|
| 153 |
+
#qwen3.6-27b
|
| 154 |
+
d_model=5120 n_prompts=1000 layers=0..62 (63) dtype=f16
|
| 155 |
+
gguf: jacobian-lens-GGUF/qwen3.6-27b-jlens.gguf
|
| 156 |
+
|
| 157 |
+
#qwen3-8b
|
| 158 |
+
d_model=4096 n_prompts=461 layers=0..34 (35) dtype=f16
|
| 159 |
+
gguf: jacobian-lens-GGUF/qwen3-8b-jlens.gguf
|
| 160 |
+
```
|