Upload GemmaForCausalLM

config.json

@@ -23,7 +23,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "torch_dtype": "float16",
-  "transformers_version": "4.42.0.dev0",
+  "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 256008
+  "vocab_size": 256000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.42.0.dev0"
+  "transformers_version": "4.41.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d0f4ff13aefd2b9e1eac807f314c9284ef6fdd30cf6d99cc6f31bb2664e730
-size 4878082904
+oid sha256:cf33fc0660c15c8705bd12210856653a00f1c1303690aa24af7dd61ed4b4c5c6
+size 4945242104

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cd9ad48bdc49d17d3a613b0e0f5f21a24e285863f60aff1bd584e8832db3375
-size 4097930816
+oid sha256:b5878fcd2e7e609e0d5d5bf539fb5f02f24b0c5a7014b1efde2f2fd766abade1
+size 67121600

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 8975994880
+    "total_size": 5012344832
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -22,78 +22,78 @@
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
@@ -148,24 +148,24 @@
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }