Upload model

model-00001.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af1f6afbe73d73e26398e7992825d24a3f49204a3bcc65a28a1030263e43e47
-size 2127523756
+oid sha256:21ac17a8bcba281201233fd7a2d05f3d511d03cd8432dab07d3c49745f8279ff
+size 2127522803

model-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a3fe4203e0fc20dd9059b7a02a8337e72e79683fd8477a183a5abf6505631e
-size 1274249800
+oid sha256:3eb83f66e29bb19568b4d81fd5efb7d59aa9ee9f744e511abfc1d33037420c13
+size 1336917858

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 3401529668
+        "total_size": 3464197717
     },
     "weight_map": {
         "model.layers.0.self_attn.q_proj.weight.shape": "model-00001.safetensors",
@@ -966,9 +966,6 @@
         "model.layers.31.post_attention_layernorm.weight.dtype": "model-00001.safetensors",
         "model.norm.weight.dtype": "model-00001.safetensors",
         "lm_head.weight.dtype": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_min": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_max": "model-00001.safetensors",
-        "model.embed_tokens.weight.shape": "model-00001.safetensors",
         "model.layers.0.self_attn.q_proj.weight.gptq_4_bit_weight_packed.shape": "model-00001.safetensors",
         "model.layers.0.self_attn.q_proj.weight.gptq_4_bit_scale.shape": "model-00001.safetensors",
         "model.layers.0.self_attn.k_proj.weight.gptq_4_bit_weight_packed.shape": "model-00001.safetensors",
@@ -1389,6 +1386,7 @@
         "model.layers.29.mlp.up_proj.weight.gptq_4_bit_scale.shape": "model-00001.safetensors",
         "model.layers.29.mlp.down_proj.weight.gptq_4_bit_weight_packed.shape": "model-00001.safetensors",
         "model.layers.29.mlp.down_proj.weight.gptq_4_bit_scale.shape": "model-00001.safetensors",
+        "model.embed_tokens.weight.shape": "model-00001.safetensors",
         "model.layers.0.input_layernorm.weight.shape": "model-00001.safetensors",
         "model.layers.0.post_attention_layernorm.weight.shape": "model-00001.safetensors",
         "model.layers.1.input_layernorm.weight.shape": "model-00001.safetensors",
@@ -1483,12 +1481,6 @@
         "model.layers.31.post_attention_layernorm.weight.shape": "model-00001.safetensors",
         "model.norm.weight.shape": "model-00001.safetensors",
         "lm_head.weight.shape": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_packed.shape": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_min.shape": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_max.shape": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_packed.dtype": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_min.dtype": "model-00001.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_max.dtype": "model-00001.safetensors",
         "model.layers.0.self_attn.q_proj.weight.gptq_4_bit_weight_packed.compressed": "model-00001.safetensors",
         "model.layers.0.self_attn.q_proj.weight.gptq_4_bit_scale.compressed": "model-00001.safetensors",
         "model.layers.0.self_attn.k_proj.weight.gptq_4_bit_weight_packed.compressed": "model-00001.safetensors",
@@ -1909,6 +1901,7 @@
         "model.layers.29.mlp.up_proj.weight.gptq_4_bit_scale.compressed": "model-00002.safetensors",
         "model.layers.29.mlp.down_proj.weight.gptq_4_bit_weight_packed.compressed": "model-00002.safetensors",
         "model.layers.29.mlp.down_proj.weight.gptq_4_bit_scale.compressed": "model-00002.safetensors",
+        "model.embed_tokens.weight.compressed": "model-00002.safetensors",
         "model.layers.0.input_layernorm.weight.compressed": "model-00002.safetensors",
         "model.layers.0.post_attention_layernorm.weight.compressed": "model-00002.safetensors",
         "model.layers.1.input_layernorm.weight.compressed": "model-00002.safetensors",
@@ -2002,7 +1995,6 @@
         "model.layers.31.input_layernorm.weight.compressed": "model-00002.safetensors",
         "model.layers.31.post_attention_layernorm.weight.compressed": "model-00002.safetensors",
         "model.norm.weight.compressed": "model-00002.safetensors",
-        "lm_head.weight.compressed": "model-00002.safetensors",
-        "model.embed_tokens.weight.manual_8_bit_weight_packed.compressed": "model-00002.safetensors"
+        "lm_head.weight.compressed": "model-00002.safetensors"
     }
 }