Upload 9 files

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<eop>": 151334,
+  "<sop>": 151333,
+  "<|assistant|>": 151337,
+  "<|begin_of_image|>": 151339,
+  "<|begin_of_video|>": 151341,
+  "<|end_of_image|>": 151340,
+  "<|end_of_video|>": 151342,
+  "<|endoftext|>": 151329,
+  "<|observation|>": 151338,
+  "<|system|>": 151335,
+  "<|user|>": 151336,
+  "[MASK]": 151330,
+  "[gMASK]": 151331,
+  "[sMASK]": 151332
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "THUDM/glm-4-9b-chat",
+  "add_bias_linear": false,
+  "add_qkv_bias": true,
+  "apply_query_key_layer_scaling": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "ChatGLMForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "auto_map": {
+    "AutoConfig": "THUDM/glm-4-9b-chat--configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "THUDM/glm-4-9b-chat--modeling_chatglm.ChatGLMForSequenceClassification"
+  },
+  "bias_dropout_fusion": true,
+  "classifier_dropout": null,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "ffn_hidden_size": 13696,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1.5625e-07,
+  "model_type": "chatglm",
+  "multi_query_attention": true,
+  "multi_query_group_num": 2,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_layers": 40,
+  "original_rope": true,
+  "pad_token_id": 151329,
+  "padded_vocab_size": 151552,
+  "post_layer_norm": true,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "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"
+  },
+  "rmsnorm": true,
+  "rope_ratio": 500,
+  "seq_length": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "max_length": 128000,
+  "pad_token_id": 151329,
+  "temperature": 0.8,
+  "top_p": 0.8,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d3fcd2b709c6e3cb60e3896a58e914925e051e3aebe944741bcc4d1d8e0936c
+size 4996990148

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bc43df0319c1605ed0e597e75bde3f7751d3814e2786b9115aa3d9dd2a8480
+size 2076390388

model.safetensors.index.json

@@ -0,0 +1,771 @@
+{
+  "metadata": {
+    "total_size": 7073273648
+  },
+  "weight_map": {
+    "transformer.embedding.word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.final_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.0.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.1.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.10.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.11.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.12.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.13.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.14.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.15.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.16.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.17.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.18.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.19.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.2.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.20.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.21.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.22.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.23.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.24.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.25.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.26.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.27.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.28.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.29.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.3.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.30.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.31.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.32.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.33.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.34.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.35.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.36.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.37.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.38.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.dense.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.dense.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.weight.absmax": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.weight.quant_map": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.39.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00002-of-00002.safetensors",
+    "transformer.encoder.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.4.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.5.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.6.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.7.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.8.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.dense.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight.absmax": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight.quant_map": "model-00001-of-00002.safetensors",
+    "transformer.encoder.layers.9.self_attention.query_key_value.weight.quant_state.bitsandbytes__fp4": "model-00001-of-00002.safetensors",
+    "transformer.output_layer.weight": "model-00002-of-00002.safetensors",
+    "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a493598071550244b2ee7f26118f3edec2150b9dfa967929a99052ac83fe716
+size 2623634

tokenizer_config.json

@@ -0,0 +1,147 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "THUDM/glm-4-9b-chat--tokenization_chatglm.ChatGLM4Tokenizer",
+      null
+    ]
+  },
+  "chat_template": "[gMASK]<sop>{% for item in messages %}{% if item['tools'] is defined %}<|system|>\n你是一个名为 ChatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。\n\n# 可用工具{% set tools = item['tools'] %}{% for tool in tools %}{% if tool['type'] == 'function' %}\n\n## {{ tool['function']['name'] }}\n\n{{ tool['function'] | tojson(indent=4) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。{% elif tool['type'] == 'python' %}\n\n## python\n\n当你向 `python` 发送包含 Python 代码的消息时，该代码将会在一个有状态的 Jupyter notebook 环境中执行。\n`python` 返回代码执行的输出，或在执行 60 秒后返回超时。\n`/mnt/data` 将会持久化存储你的文件。在此会话中，`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用，这些在线内容的访问将不会成功。{% elif tool['type'] == 'simple_browser' %}\n\n## simple_browser\n\n你可以使用 `simple_browser` 工具。该工具支持以下函数：\n`search(query: str, recency_days: int)`：使用搜索引擎进行查询并显示结果，可以使用 `recency_days` 参数控制搜索内容的时效性。\n`mclick(ids: list[int])`：获取一系列指定 id 的页面内容。每次调用时，须选择3-10个页面。选择多个角度的页面，同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的，你也可以多打开一些可能有用的页面而不用担心内容过多。\n`open_url(url: str)`：打开指定的 URL。\n\n使用 `【{引用 id}†{引用文本}】` 来引用内容。\n\n操作步骤：1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。\n 如果用户提供了 URL，也可以用 `open_url` 直接打开页面。\n如果初次搜索结果没有找到合适的信息，也可以再次使用 `search` 进行搜索。{% elif tool['type'] == 'cogview' %}\n\n## cogview\n\n如果用户的请求中包含了对图像的描述，你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述，规则：\n- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。\n- 应当尽可能详细地描述图像生成的需求，需求描述约 100 英文单词。\n- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。\n- 如无特殊说明，所在地为中国，持有中国立场并遵循中国社会主义价值观。{% endif %}{% endfor %}{% endif %}{% if item['content'] %}<|{{ item['role'] }}|>{{ item['metadata'] }}\n{{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "ChatGLM4Tokenizer"
+}