Adding `safetensors` variant of this model

model.safetensors.index.json

@@ -0,0 +1,170 @@
+{
+    "metadata": {
+        "total_size": 2593656832
+    },
+    "weight_map": {
+        "lm_head.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.0.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.0.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.0.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.1.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.1.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.1.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.10.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.10.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.10.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.11.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.11.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.11.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.12.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.12.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.12.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.13.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.13.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.13.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.14.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.14.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.14.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.15.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.15.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.15.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.2.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.2.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.2.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.3.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.3.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.3.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.4.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.4.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.4.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.5.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.5.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.5.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.6.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.6.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.6.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.7.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.7.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.7.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.8.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.8.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.8.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.input_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.mlp.down_proj.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.9.mlp.down_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.mlp.gate_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.mlp.up_proj.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.post_attention_layernorm.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.self_attention.dense.bias": "model_00001-of-00001.safetensors",
+        "transformer.h.9.self_attention.dense.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.self_attention.key_value.weight": "model_00001-of-00001.safetensors",
+        "transformer.h.9.self_attention.query.weight": "model_00001-of-00001.safetensors",
+        "transformer.ln_f.weight": "model_00001-of-00001.safetensors",
+        "transformer.word_embeddings.weight": "model_00001-of-00001.safetensors"
+    }
+}

model_00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df3674b84f8651c076d331ead158fae747fce40691a1525f9e84f545d8bc09b
+size 2593675832