初始化项目,由ModelHub XC社区提供模型
Model: Polygl0t/Tucano2-qwen-1.5B-Think Source: Original Platform
This commit is contained in:
3
.plots/apo_gradient_norm.png
Normal file
3
.plots/apo_gradient_norm.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:29bd25077d0963148cb0f4037f0cb8dc118a541def9d889dfefddb3f8aeb09de
|
||||
size 482994
|
||||
3
.plots/apo_reward.png
Normal file
3
.plots/apo_reward.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3ab2d18bdb9961ad8a8bc0e7274735ebb2c337e2ed2cc389b3b00f81c1e66f7e
|
||||
size 286839
|
||||
3
.plots/model_comparison.png
Normal file
3
.plots/model_comparison.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d798bab25626567c5d6b038d5631782671b04b10684a06daaff40297925e01a8
|
||||
size 217771
|
||||
3
.plots/sft_gradient_norm.png
Normal file
3
.plots/sft_gradient_norm.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0de46cb25883cd57d12cb8e6fa41c6e810a209b7ce2e3d797ca5f41831a9f3da
|
||||
size 318225
|
||||
3
.plots/sft_loss.png
Normal file
3
.plots/sft_loss.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c38664279e9165a2b64c2e062894747b34f55953834b96c7613089c0000d39fe
|
||||
size 383372
|
||||
Reference in New Issue
Block a user