Upload folder using huggingface_hub

text_encoder_2/config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "black-forest-labs/FLUX.1-Depth-dev",
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

text_encoder_2/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4b559411fbef7373773f43600bd2fe7761c4bf167b9652685ff66d21e86d62
+size 4897241034

text_encoder_2/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6f84c01f1105e5899d70a9944d86bf4b2e8b9063b994884d05ab86090f3220
+size 1431426998

text_encoder_2/model.safetensors.index.json

@@ -0,0 +1,658 @@
+{
+  "metadata": {
+    "total_size": 6328582736
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight.absmax": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight.quant_map": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "shared.weight": "model-00001-of-00002.safetensors"
+  }
+}

transformer/config.json

@@ -0,0 +1,35 @@
+{
+  "_class_name": "FluxTransformer2DModel",
+  "_diffusers_version": "0.32.0.dev0",
+  "_name_or_path": "black-forest-labs/FLUX.1-Depth-dev",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    16,
+    56,
+    56
+  ],
+  "guidance_embeds": true,
+  "in_channels": 128,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 19,
+  "num_single_layers": 38,
+  "out_channels": 64,
+  "patch_size": 1,
+  "pooled_projection_dim": 768,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  }
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec232c2fadb539361a8ebd34f739e9e15c31a2fce7e50f265198721671e313bf
+size 6699492648