Training in progress, epoch 2

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba58e656ccc9afc5ac24fd48c6b4fabe3c6f0fdeeb5196ec3cbf5df995a2398
+size 4965801344

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c75a796022bbde1831ad83fdd813a6885c854958018592d0c74df77a250fa9
+size 1547842640

model.safetensors.index.json

@@ -0,0 +1,269 @@
+{
+  "metadata": {
+    "total_size": 6513610752
+  },
+  "weight_map": {
+    "cross_attention.Wkv.bias": "model-00002-of-00002.safetensors",
+    "cross_attention.Wkv.weight": "model-00002-of-00002.safetensors",
+    "cross_attention.Wq.bias": "model-00002-of-00002.safetensors",
+    "cross_attention.Wq.weight": "model-00002-of-00002.safetensors",
+    "cross_attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "cross_attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "image_proj.bias": "model-00002-of-00002.safetensors",
+    "image_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "llama_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "llama_model.model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0418f5deb30faa4e4118e591ae96692cb0626f2762a09f208b48562514c3c1b
+oid sha256:4b98c07ee1994bcc03bd5d507efed729bcd395fce7601eb2e411b564467ea482
 size 6456