Upload 9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer

final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer/config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "Flux2Transformer2DModel",
+  "_diffusers_version": "0.39.0",
+  "_name_or_path": "black-forest-labs/FLUX.2-klein-base-9B",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    32,
+    32,
+    32
+  ],
+  "eps": 1e-06,
+  "guidance_embeds": false,
+  "in_channels": 128,
+  "joint_attention_dim": 12288,
+  "mlp_ratio": 3.0,
+  "num_attention_heads": 32,
+  "num_layers": 8,
+  "num_single_layers": 24,
+  "out_channels": null,
+  "patch_size": 1,
+  "rope_theta": 2000,
+  "timestep_guidance_channels": 256
+}

final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer/diffusion_pytorch_model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28b98c4a5fcf7ce1f53a438c604b8fcd21a831d2ac559c402436461fde3e289
+size 9804206048

final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer/diffusion_pytorch_model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4bc112c3af7ed1ec2f03dc03610cdf708cd7d920cf69620f4dc0a001f729b96
+size 9797913704

final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer/diffusion_pytorch_model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec91abc8499de87d28edda44532089bf20a32b3458ccaf7aff900983185917e
+size 9596584288

final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer/diffusion_pytorch_model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee511fc7285743d58f5fd64d5fc44c72111db4d2c976290ef6ba3e7ccf074e35
+size 7115649136

final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,240 @@
+{
+  "metadata": {
+    "total_size": 36314324992
+  },
+  "weight_map": {
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "double_stream_modulation_img.linear.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "double_stream_modulation_txt.linear.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_stream_modulation.linear.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "single_transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.0.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.0.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.1.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.1.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.10.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.10.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.11.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.11.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.12.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.12.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.13.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.13.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.14.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.14.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.15.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.15.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.16.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.16.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.17.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.17.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.18.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.18.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.19.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.19.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.2.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.2.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.20.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.20.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.20.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.20.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.21.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.21.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.21.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.21.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.22.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.22.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.22.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.22.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.23.attn.norm_k.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.23.attn.norm_q.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.23.attn.to_out.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.23.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00004-of-00004.safetensors",
+    "single_transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.3.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.3.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.4.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.4.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "single_transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.5.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.5.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.6.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.6.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.7.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.7.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.8.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.8.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.9.attn.to_out.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "single_transformer_blocks.9.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00003-of-00004.safetensors",
+    "time_guidance_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "time_guidance_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.0.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.1.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.2.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.3.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00004.safetensors",
+    "transformer_blocks.4.ff_context.linear_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.ff_context.linear_in.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.5.ff_context.linear_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.ff_context.linear_in.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.6.ff_context.linear_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.add_k_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.add_q_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.add_v_proj.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.norm_added_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.norm_added_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.to_add_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.to_k.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.to_out.0.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.to_q.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.attn.to_v.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.ff.linear_in.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.ff.linear_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.ff_context.linear_in.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "transformer_blocks.7.ff_context.linear_out.weight": "diffusion_pytorch_model-00002-of-00004.safetensors",
+    "x_embedder.weight": "diffusion_pytorch_model-00001-of-00004.safetensors"
+  }
+}

final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer/merge_manifest.json

@@ -0,0 +1,125 @@
+{
+  "command": [
+    "scripts/models/merge_diffusers_transformers.py",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-75000",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-80000",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-85000",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-87500",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-90000",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-92500",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-95000",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-97500",
+    "1",
+    "--model",
+    "final_models/9B/nonzeroshot/checkpoint-100000",
+    "1",
+    "--output",
+    "final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer"
+  ],
+  "created_at_utc": "2026-09-17T17:27:27.887473+00:00",
+  "format": "open_visionbanana.diffusers_transformer_merge.v1",
+  "ignored_config_fields": [
+    "_name_or_path"
+  ],
+  "inputs": [
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-75000/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-80000/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-85000/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-87500/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-90000/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-92500/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-95000/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-97500/transformer"
+    },
+    {
+      "config_sha256": "34ec7b602e2372bf272fa7a07a85280bea6efcbda5f3253e1d6ef1a375b8eabb",
+      "index_sha256": "235a30e4d3ac93b6eaf483fe690af3d302d18b9e883878695fa60aff5ff0818b",
+      "normalized_weight": 0.1111111111111111,
+      "requested_weight": 1.0,
+      "transformer": "final_models/9B/nonzeroshot/checkpoint-100000/transformer"
+    }
+  ],
+  "method": "convex_weighted_average",
+  "output": "final_models/9B/nonzeroshot/checkpoint-avg75000-100000_drop77500_82500/transformer",
+  "shards": [
+    {
+      "name": "diffusion_pytorch_model-00001-of-00004.safetensors",
+      "size_bytes": 9804206048
+    },
+    {
+      "name": "diffusion_pytorch_model-00002-of-00004.safetensors",
+      "size_bytes": 9797913704
+    },
+    {
+      "name": "diffusion_pytorch_model-00003-of-00004.safetensors",
+      "size_bytes": 9596584288
+    },
+    {
+      "name": "diffusion_pytorch_model-00004-of-00004.safetensors",
+      "size_bytes": 7115649136
+    }
+  ],
+  "tensor_count": 233
+}