Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- early_exit_20250817_layers_5_kl0_25/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_1000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_1500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_2000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_2500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_25/step_2500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_3000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_3500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_4000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_4500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_25/step_500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_5000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_25/step_5500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_25/step_5500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_1000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_1000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_1500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_1500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_2000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_2000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_2500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_2500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_3000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_3000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_3500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_3500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_4000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_4000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_4500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_4500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl0_5/step_500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl0_5/step_500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_1000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_1000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_1500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_1500/early_exiter/adapter_config.json +39 -0
- early_exit_20250817_layers_5_kl1_0/step_1500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_2000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_2000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_2500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_2500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_3000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_3000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_3500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_3500/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_4000/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_4000/early_exiter/adapter_model.safetensors +3 -0
- early_exit_20250817_layers_5_kl1_0/step_500/early_exit_probes.pt +3 -0
- early_exit_20250817_layers_5_kl1_0/step_500/early_exiter/adapter_model.safetensors +3 -0
early_exit_20250817_layers_5_kl0_25/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07837de4aac568f367b773a9fa7c83f63f00f79a6d55285ede23a8cd33f7e90b
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_1000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:010178105f916551ad0e5d249749cd4f1803a83364379b32ee016abcb12fb621
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_1500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c6b229cea6a622adad4cd83d103ca4db4774600fa328fdb6e11c63d006f7b5
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_2000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a1bad52e342572ba7f37faacbbb6db8850d2804f115672f53ebb2bacae55118
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_2500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17ce5b5621baa8bc69de1301911eb87994c562c78e7a870e957f14154a691096
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_25/step_2500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fca6ee0bfcb5f572d767cd95f743813ffa219b31e9ca7769cd597cdf90fb555
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_3000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70ea8e8ac529c747fee3326a8bc3c0af36e9749fa7226346dbf2daf5d804abdc
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_3500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:273af2867436e58e50844b183f496953a4322f2106174f65cdf8f4752710bfac
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_4000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6c504a4c9d3352c31e0583c783347cbea637d3ff9fcf44bcfacf13844cf2d5c
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_4500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04963cfbcdc9cd2dc389e7e28a770239911ce9b334576d08b2893eb1694ee9b5
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f05a8849df30e7f4627109595f9ff10dede74411779cb8d35331b0bb76d19677
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_25/step_500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f360088c05bc92e8d3c4eabc91db63a3e2724e36c03e275f5cac29a042c09f0d
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_5000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f428af5b13e6cc0afa86eb5ce37f81fe889be900ce84bbd46e0e4e322327284e
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_25/step_5500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74449800989026130ff27bcae1274e725e5d5ca92814d200c2e706d9661a7107
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_25/step_5500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45f16f652cbae6a07047c1a4051ae50fb9a5e60bc186065030005485e8d0caf8
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_1000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33738442e1247e815fb2c500345319a5563d04000652fb2e24ec3b99631a06d7
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_1000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d3fe9a2492170a213e876e838e3694e7e11842a1ce16a69a3ed4abd97c25142
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_1500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4fe2e83d79187c01397242bd31b08951ec9a17c2aa4835fbf217ae214dd6d30
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_1500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4238b92fcab22412d76d75193cd25ef6ecce70cd3e73786b9a0a08e95b7827f4
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_2000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07e05a05fe400df853f1ef976108852b8cfe0295578167ed8d2a111866ccae22
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_2000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8fddb33783b5d1b9cf4a8746b02ff240ae871abf2dce3330173431ad59361248
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_2500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91c0aab502ac28109143132ed98849852ecd804a375003ebbd18fe1e52923b32
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_2500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9971aa1129ada0584e6c8a881b75d64dc119a3651edb778fd0b1ec9e46ec7da
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_3000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a8bada79a15e7fc2e3273cdc44976607af137b163ba7c4d6b2ffa68f21c7953
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_3000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:327823a4df4fc17121bca57111c7eae599c1f1a8da3557fe6062b04ef0f15218
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_3500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab59da6ad5bfc19e5a30e46d734f6a96c6c39d0944edd864d2e2e9846d739865
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_3500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05631d45d62b040edcaa295a2ac561aa67530432eaec2821d182d533d66ceeee
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_4000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90bce4068ab86d26f73141badfd7c856f5c9b1d1ccf8087fc4a1e6eff1043f8e
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_4000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f6fca8b465a580576bb9f3ac7fa32011667086d054c3183f59159d1f3349b2e
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_4500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fadbb614b7b2e1ae2a48dbd34e074dbab0461f72fd0d28db48104551f001abb8
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_4500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feac8841f6756b1981e6a780263c2680488263b65383c3b489cab58ee633cb9a
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl0_5/step_500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:233b532b92f23ae96259c7f005df971212582b60258c503bea00d10dee942ad5
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl0_5/step_500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cbf678583da0b9b3730d4d0cc24bd3d8fa2717f8bb7e850c073eee856ece348
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_1000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d35f90cc59f64cb79f5adca290507cbe08e0633d63d38c295c99e6062c78f2af
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_1000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1546154ad4bd130bcfbcad7a9a31becf48dea2522da6ad21ee711c0e3ca8cacc
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_1500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d8a81f3799794e66bb9b4bcea4f0d4e8b397eef8f497bc18e34fcb35a64477e
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_1500/early_exiter/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
+
"r": 16,
|
| 25 |
+
"rank_pattern": {},
|
| 26 |
+
"revision": null,
|
| 27 |
+
"target_modules": [
|
| 28 |
+
"q_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"v_proj",
|
| 31 |
+
"k_proj"
|
| 32 |
+
],
|
| 33 |
+
"target_parameters": null,
|
| 34 |
+
"task_type": "CAUSAL_LM",
|
| 35 |
+
"trainable_token_indices": null,
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_qalora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
early_exit_20250817_layers_5_kl1_0/step_1500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c07cad6c04a6b209c5d30f349968e875250093ebacc2f5064fa5abe35d2c47f
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_2000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab939b589ea04dccc46699e69076fbcb4e563be64155220671927656e11ef621
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_2000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8aba5d4d6e46b2e580e3d233607894b8f0064fcb1d6cf3565a747de5f1abb8a
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_2500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3d0c199a29a0bd6e6e3d36923f986dc9e50cea94ca49c5f760b5aa9afa8ed47
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_2500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90793ab06310160794c6cdaba44f64957b59ee903ca487c7e28ba9bfd3c2b970
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_3000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0bc46a32522eeb22fc65dda72ec2ea23a26d524ee6312685b2cee5999431f42
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_3000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b75ffc50b1284f9b6ce5897a58dfa59448c51a4ca3b92fb3c68d50a7e4f9e2dc
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_3500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e798c99ca4ef518c1ed0553c037dab3cccab3424a51d894cdb84d1b6c5d6773
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_3500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3bad102aabb761b5ef950fb7864d5ffb697f128e45d37e97d331b1502e0de78
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_4000/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aee0950af96d5b2e7519d64e713ac98af1b6df3714f39612874b686099f87c18
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_4000/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38eae4c6bbce7689260103bf71cd539d4b887c11dd61243026feb7972fc2b1ec
|
| 3 |
+
size 1884453408
|
early_exit_20250817_layers_5_kl1_0/step_500/early_exit_probes.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:463833d32818b0f56ee21cb0057493ee25c4500b2f66051075ca79a27894df29
|
| 3 |
+
size 94502251
|
early_exit_20250817_layers_5_kl1_0/step_500/early_exiter/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68fa34fabf333552510d2cb3a2fee13a55f30ac4f9d0b5eaeefb9c946c3cb8a6
|
| 3 |
+
size 1884453408
|