Upload Gemma2ForCausalLM

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/data/jupyterlab/hometax/axolotl/outputs/EL-MT40/merged",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a304294afb4f26d6d8127cc8062c39e03ad8c12d5089d1fa98495e07a353c9
+size 4844480456

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b39472903a441f6c37395f63d5e3daeb8c326f2f43c67c77061dbadd5cebb7
+size 4962213464

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4f1fdb3e6f6f3fc178e4a76f5112b65a33e25b50f64decf35b54226847be20
+size 4962271312

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6284760a808e0dd74632d67fc718618276142f80eae42b2afa8e284ea31773c7
+size 4932853744

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34bce6b0f3db34a30dd727558ed4ffaec6dec09fd56ce52940bca025a4fdfb95
+size 4962213528

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ee765da8deb07489a41ec4d0a7221d09182e4259a937af9d00d9b8cb1dc20e
+size 4962213528

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d2e8af5ac2db9d7a90185fc80c8464af12493b0395c5f4706157efba2bb0e4
+size 4962271328

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66eb045c8690e60e8221a41a33b37c9786948ffa0cdc296a12d9f01d26bf4a71
+size 2378360680

model.safetensors.index.json

@@ -0,0 +1,471 @@
+{
+  "metadata": {
+    "total_size": 36966823936
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
+  }
+}