Upload MllamaForCausalLM

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "MllamaForCausalLM"
+  ],
+  "bos_token_id": 128000,
+  "cross_attention_layers": [
+    3,
+    8,
+    13,
+    18,
+    23,
+    28,
+    33,
+    38
+  ],
+  "dropout": 0,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mllama_text_model",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": true,
+  "vocab_size": 158942
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13dfcfdc30a51d196d72ac04f62e24330f9320fb4f67a845132b1b4c0c48cefe
+size 4986538832

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66132f76bfdc4be3e154d786ef9f607f8b14b097799f94956a30588f8ca3f55a
+size 4999832488

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8a1f70f8b481473c50a83f75d037f809fe1b680c0936dfa48a9d50240f6098b
+size 4999798080

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0927d95ea5d3d94141e2573415f516aec2ef78776c7ea10db46f00a75af5a66c
+size 4832008968

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76775f8e167873081ccd5f6630fc5234dc7a0e69f9e6583d1a0f2102c00d743
+size 4999814592

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc49a36100daa7cd1e3d0965debf30ddded2bc909d59f8485f3dc4f461c4888
+size 4999814600

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac8a94427121283581af2039437a5fda8fa835b3916b41dd88ab8608fe4ff4b
+size 4832008968

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014d67052c89c119c6bee0c3840ff88364ec6cd5a15b32ec9290abf18ce3757a
+size 2852279216

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2769ee7c8d5c1a8f1badaaedd0bcdc3963eadc65dafb58aa598c116dc4ed268a
+size 2604105856

model.safetensors.index.json

@@ -0,0 +1,402 @@
+{
+  "metadata": {
+    "total_size": 40106156096
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn.k_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn.q_norm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn_attn_gate": "model-00003-of-00009.safetensors",
+    "model.layers.13.cross_attn_mlp_gate": "model-00003-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn.k_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn.q_norm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn_attn_gate": "model-00004-of-00009.safetensors",
+    "model.layers.18.cross_attn_mlp_gate": "model-00004-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn.k_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn.q_norm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn_attn_gate": "model-00005-of-00009.safetensors",
+    "model.layers.23.cross_attn_mlp_gate": "model-00005-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn.k_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn.q_norm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn_attn_gate": "model-00006-of-00009.safetensors",
+    "model.layers.28.cross_attn_mlp_gate": "model-00006-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.3.cross_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.cross_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.cross_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.cross_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.cross_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.cross_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.cross_attn_attn_gate": "model-00002-of-00009.safetensors",
+    "model.layers.3.cross_attn_mlp_gate": "model-00002-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn.k_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn.q_norm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn_attn_gate": "model-00007-of-00009.safetensors",
+    "model.layers.33.cross_attn_mlp_gate": "model-00007-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn.k_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn.q_norm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn_attn_gate": "model-00008-of-00009.safetensors",
+    "model.layers.38.cross_attn_mlp_gate": "model-00008-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn.k_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn.q_norm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn_attn_gate": "model-00002-of-00009.safetensors",
+    "model.layers.8.cross_attn_mlp_gate": "model-00002-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.norm.weight": "model-00008-of-00009.safetensors"
+  }
+}