Upload GemmaForCausalLM

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/223040239/medbase/ckpts/gemma-7ballsft/checkpoint-0-36650/tfmr",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f643539e470dc299b79c38ded47cf0fc2677a7883b83715bc9acc0b5006d650
+size 4756367064

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13947e666d452d2029368a22aa79e32f4ce17c9a192b5e4bfc003b4ba7706d12
+size 4731277472

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8177a37bbd1d1641c438a9b79097823b192d346a08c8fed5938e23eb707ede69
+size 4932629344

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6fe74060a4eaa842518331f8901a28f79399c5a64db4175c1f7f7a84d317b4
+size 4731277512

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10545b6097ae912e8492a366f399ab167283df803df8975c13c8744898f2c875
+size 4731277512

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d6a61fe93f4e517fe6531dd373463fa4db326894e4bd0a65380ca95eb29c12
+size 4932629384

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68c3f189c530b08c2fac3e87d5f6bec07903e7c27ae07729e23d478ceb19ff0
+size 4731277512

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3683ec1dbdfcf6b2357b3d42c63cb96b67a1c9640a2d098de659095690948cd
+size 604017208

model.safetensors.index.json

@@ -0,0 +1,261 @@
+{
+  "metadata": {
+    "total_size": 34150723584
+  },
+  "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.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.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-00004-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-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-00004-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-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-00005-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-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.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-00006-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-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.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.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.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.5.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-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-00003-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-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.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.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"
+  }
+}