Add trained SciWorld model.

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "LlamaModel"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb155dc88f970bbf13d58fbee1d6b6149d3723332ee8102b99bca07c06c3486
-size 4965797976
+oid sha256:05afea612fb4c652e6489f02313b58eae59940cd37c0c3aec6ad1416850c99fb
+size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f31587d3758d70c6c49f0d04c638e20d0eea70effb1f2f6e8b2d22736ee732
-size 1459729544
+oid sha256:4bf0b06b8ea7b967fe859dbe34708b679d199eaae69ddfbf9e3d29c1d0a032bb
+size 1459729952

model.safetensors.index.json

@@ -4,259 +4,259 @@
     "total_size": 6425499648
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "norm.weight": "model-00002-of-00002.safetensors"
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }