updating model files

config.json

@@ -7,12 +7,12 @@
   "params_args_dict": {
     "apply_qk_norm": true,
     "attn_activation": null,
-    "attn_name": "auto",
+    "attn_name": "xformers_attn",
     "attn_seq_scalar": null,
     "attn_seq_scalar_alpha": null,
-    "dim": 2560,
+    "dim": 2048,
     "ffn_type": "swiglu",
-    "model": "open_lm_3b",
+    "model": "open_lm_1b",
     "model_norm": "gain_only_lp_layer_norm",
     "moe_capacity_factor": 1.25,
     "moe_expert_model_parallelism": false,
@@ -21,8 +21,8 @@
     "moe_num_experts": null,
     "moe_top_k": 2,
     "moe_weight_parallelism": false,
-    "n_heads": 32,
-    "n_layers": 32,
+    "n_heads": 16,
+    "n_layers": 24,
     "norm_eps": 1e-05,
     "positional_embedding_type": "rotary",
     "post_embed_norm": false,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cffdaf2c5e5995b3534da7d3a35e88d09fd5598991a59fe8bbd8f7c735ec2a30
+oid sha256:ffde86b5ee582d035731e87351e3e387f9d4e583ae10d38a0616c6528e55d051
 size 4985679432

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:306afc949d95425e74076426939757d50b9a30e957300da62736d36d6da6c97d
+oid sha256:701970bfc552ed8a0afe03570595589eb110d0a0e60c526d9ffce6147f672856
 size 773925424

model.safetensors.index.json

@@ -1,298 +1,226 @@
 {
   "metadata": {
-    "total_size": 11184389120
+    "total_size": 5759580160
   },
   "weight_map": {
-    "model.layers.0.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.0.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.1.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.10.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.11.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.12.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.12.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.13.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.13.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.14.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.14.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.15.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.16.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.17.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.18.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.19.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.2.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.20.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.21.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.22.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.23.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.24.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.24.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.25.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.25.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.26.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.26.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.27.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.27.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.28.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.attention_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.feed_forward.w12.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.feed_forward.w3.weight": "model-00002-of-00003.safetensors",
-    "model.layers.28.ffn_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.attention.in_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.attention.k_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.attention.out_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.attention.pos_embed.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.29.attention.q_norm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.29.attention_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.ffn_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.3.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.30.attention.in_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.attention.k_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.attention.out_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.30.attention.q_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.attention_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.ffn_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.attention.in_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.attention.k_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.attention.out_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.attention.pos_embed.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.31.attention.q_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.attention_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.feed_forward.w12.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.feed_forward.w3.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.ffn_norm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.4.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.4.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.5.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.6.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.7.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.8.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.attention.in_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.attention.k_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.attention.out_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.attention.pos_embed.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.9.attention.q_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.attention_norm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.feed_forward.w12.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.feed_forward.w3.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.ffn_norm.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors",
-    "model.output.weight": "model-00003-of-00003.safetensors",
-    "model.tok_embeddings.weight": "model-00001-of-00003.safetensors"
+    "model.layers.0.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attention.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.pos_embed.inv_freq": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w12.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.in_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.pos_embed.inv_freq": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w12.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.in_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.pos_embed.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w12.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.output.weight": "model-00002-of-00002.safetensors",
+    "model.tok_embeddings.weight": "model-00001-of-00002.safetensors"
   }
 }