Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a02c9384f0ac15ec3b2c37f82306449308c8f3fe01e7cb966f1adba15cba8ba8
-size 5354888445
+oid sha256:6a803fa7da14abccba67fd173045831db43d83f4714b058f267e5ac20de47bf9
+size 5153392166

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ff58c2be574febac84eff7a5f3168fa5da9a839b0c41df9cf84b4681ead5f0
-size 3749723058
+oid sha256:cb0162a4d0659df905740556bd562ead0b4a7fd42d55a28089c915837b25a304
+size 1291001325

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 9104484160
+        "total_size": 6444266400
     },
     "weight_map": {
         "language_model.lm_head.biases": "model-00002-of-00002.safetensors",
@@ -264,9 +264,9 @@
         "language_model.model.blocks.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.23.attn_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.23.ff_norm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.blocks.23.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.23.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.23.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.blocks.23.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.23.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.23.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.23.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.23.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.23.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
@@ -278,102 +278,102 @@
         "language_model.model.blocks.23.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.blocks.24.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.blocks.24.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.3.attn_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.3.ff_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.3.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
@@ -390,102 +390,102 @@
         "language_model.model.blocks.3.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.blocks.30.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.attn_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.ff_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.mlp.ff_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.mlp.ff_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.mlp.ff_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.mlp.ff_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.mlp.ff_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.mlp.ff_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.att_proj.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.att_proj.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.att_proj.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.attn_out.biases": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.attn_out.scales": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.attn_out.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-        "language_model.model.blocks.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.blocks.30.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.30.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.32.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.33.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.34.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.attn_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.ff_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.mlp.ff_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.mlp.ff_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.mlp.ff_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.mlp.ff_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.mlp.ff_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.att_proj.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.att_proj.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.att_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.attn_out.biases": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.attn_out.scales": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.blocks.35.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.4.attn_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.4.ff_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.4.mlp.ff_out.biases": "model-00001-of-00002.safetensors",
@@ -582,7 +582,7 @@
         "language_model.model.blocks.9.self_attn.attn_out.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
         "language_model.model.blocks.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-        "language_model.model.ln_f.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.ln_f.weight": "model-00001-of-00002.safetensors",
         "language_model.model.wte.embedding": "model-00001-of-00002.safetensors",
         "language_model.model.wte.new_embedding": "model-00001-of-00002.safetensors",
         "vision_tower.image_pooling_2d.wk.bias": "model-00002-of-00002.safetensors",