Upload 4B/zeroshot/checkpoint-97500/transformer

final_models/4B/zeroshot/checkpoint-97500/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-4B",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    32,
+    32,
+    32
+  ],
+  "eps": 1e-06,
+  "guidance_embeds": false,
+  "in_channels": 128,
+  "joint_attention_dim": 7680,
+  "mlp_ratio": 3.0,
+  "num_attention_heads": 24,
+  "num_layers": 5,
+  "num_single_layers": 20,
+  "out_channels": null,
+  "patch_size": 1,
+  "rope_theta": 2000,
+  "timestep_guidance_channels": 256
+}

final_models/4B/zeroshot/checkpoint-97500/transformer/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc837ca24f93c445929e1ae9ff84061707e6795025c5345823ac98306865808e
+size 9876047152

final_models/4B/zeroshot/checkpoint-97500/transformer/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c9743337b5a473fa754c5325038f32f4483e55303c27182f5f267474e51fdce
+size 5626151600

final_models/4B/zeroshot/checkpoint-97500/transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,176 @@
+{
+  "metadata": {
+    "total_size": 15502178304
+  },
+  "weight_map": {
+    "context_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "double_stream_modulation_img.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "double_stream_modulation_txt.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "norm_out.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "proj_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_stream_modulation.linear.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.0.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.1.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.10.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.11.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.12.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.13.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.14.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.15.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.16.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.17.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.18.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.19.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.2.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.3.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.4.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.5.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.6.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.to_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.7.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.8.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.to_out.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "single_transformer_blocks.9.attn.to_qkv_mlp_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "time_guidance_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "time_guidance_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.0.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.1.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.2.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.3.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_q_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.add_v_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_added_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_added_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_add_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.attn.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.linear_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "transformer_blocks.4.ff_context.linear_out.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "x_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}