Upload 7 files

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.52.4"
+}

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -13,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -35,10 +35,10 @@
   "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizerFast",
+  "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

trainer_state.json

@@ -0,0 +1,545 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 735,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.040878896269800714,
+      "grad_norm": 6.032278537750244,
+      "learning_rate": 0.00019755102040816327,
+      "loss": 2.6293,
+      "step": 10
+    },
+    {
+      "epoch": 0.08175779253960143,
+      "grad_norm": 3.237109899520874,
+      "learning_rate": 0.0001948299319727891,
+      "loss": 2.008,
+      "step": 20
+    },
+    {
+      "epoch": 0.12263668880940215,
+      "grad_norm": 2.7581236362457275,
+      "learning_rate": 0.000192108843537415,
+      "loss": 1.855,
+      "step": 30
+    },
+    {
+      "epoch": 0.16351558507920286,
+      "grad_norm": 3.083601474761963,
+      "learning_rate": 0.00018938775510204083,
+      "loss": 1.7576,
+      "step": 40
+    },
+    {
+      "epoch": 0.20439448134900357,
+      "grad_norm": 2.7807652950286865,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 1.7434,
+      "step": 50
+    },
+    {
+      "epoch": 0.2452733776188043,
+      "grad_norm": 2.6213436126708984,
+      "learning_rate": 0.00018394557823129252,
+      "loss": 1.682,
+      "step": 60
+    },
+    {
+      "epoch": 0.286152273888605,
+      "grad_norm": 2.6907846927642822,
+      "learning_rate": 0.00018122448979591838,
+      "loss": 1.6749,
+      "step": 70
+    },
+    {
+      "epoch": 0.3270311701584057,
+      "grad_norm": 5.332385540008545,
+      "learning_rate": 0.00017850340136054421,
+      "loss": 1.5744,
+      "step": 80
+    },
+    {
+      "epoch": 0.36791006642820645,
+      "grad_norm": 3.23760986328125,
+      "learning_rate": 0.00017578231292517008,
+      "loss": 1.5338,
+      "step": 90
+    },
+    {
+      "epoch": 0.40878896269800713,
+      "grad_norm": 3.479809522628784,
+      "learning_rate": 0.00017306122448979594,
+      "loss": 1.4143,
+      "step": 100
+    },
+    {
+      "epoch": 0.44966785896780787,
+      "grad_norm": 2.7317419052124023,
+      "learning_rate": 0.0001703401360544218,
+      "loss": 1.4603,
+      "step": 110
+    },
+    {
+      "epoch": 0.4905467552376086,
+      "grad_norm": 2.8279190063476562,
+      "learning_rate": 0.00016761904761904763,
+      "loss": 1.5169,
+      "step": 120
+    },
+    {
+      "epoch": 0.5314256515074093,
+      "grad_norm": 3.096827983856201,
+      "learning_rate": 0.0001648979591836735,
+      "loss": 1.4396,
+      "step": 130
+    },
+    {
+      "epoch": 0.57230454777721,
+      "grad_norm": 2.9124717712402344,
+      "learning_rate": 0.00016217687074829932,
+      "loss": 1.3824,
+      "step": 140
+    },
+    {
+      "epoch": 0.6131834440470108,
+      "grad_norm": 3.073765754699707,
+      "learning_rate": 0.00015945578231292519,
+      "loss": 1.3974,
+      "step": 150
+    },
+    {
+      "epoch": 0.6540623403168114,
+      "grad_norm": 2.5229296684265137,
+      "learning_rate": 0.00015673469387755102,
+      "loss": 1.4211,
+      "step": 160
+    },
+    {
+      "epoch": 0.6949412365866121,
+      "grad_norm": 2.8301663398742676,
+      "learning_rate": 0.00015401360544217688,
+      "loss": 1.3567,
+      "step": 170
+    },
+    {
+      "epoch": 0.7358201328564129,
+      "grad_norm": 2.6760520935058594,
+      "learning_rate": 0.00015129251700680274,
+      "loss": 1.3552,
+      "step": 180
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 2.741240978240967,
+      "learning_rate": 0.00014857142857142857,
+      "loss": 1.408,
+      "step": 190
+    },
+    {
+      "epoch": 0.8175779253960143,
+      "grad_norm": 2.028970956802368,
+      "learning_rate": 0.00014585034013605443,
+      "loss": 1.3497,
+      "step": 200
+    },
+    {
+      "epoch": 0.858456821665815,
+      "grad_norm": 2.6956677436828613,
+      "learning_rate": 0.00014312925170068027,
+      "loss": 1.3592,
+      "step": 210
+    },
+    {
+      "epoch": 0.8993357179356157,
+      "grad_norm": 2.448338270187378,
+      "learning_rate": 0.00014040816326530613,
+      "loss": 1.3309,
+      "step": 220
+    },
+    {
+      "epoch": 0.9402146142054164,
+      "grad_norm": 2.267707347869873,
+      "learning_rate": 0.00013768707482993196,
+      "loss": 1.329,
+      "step": 230
+    },
+    {
+      "epoch": 0.9810935104752172,
+      "grad_norm": 2.4610676765441895,
+      "learning_rate": 0.00013496598639455782,
+      "loss": 1.3194,
+      "step": 240
+    },
+    {
+      "epoch": 1.0204394481349004,
+      "grad_norm": 2.539577007293701,
+      "learning_rate": 0.00013224489795918368,
+      "loss": 1.2862,
+      "step": 250
+    },
+    {
+      "epoch": 1.0613183444047012,
+      "grad_norm": 2.377258777618408,
+      "learning_rate": 0.00012952380952380954,
+      "loss": 1.2052,
+      "step": 260
+    },
+    {
+      "epoch": 1.1021972406745018,
+      "grad_norm": 2.4516634941101074,
+      "learning_rate": 0.00012680272108843538,
+      "loss": 1.1859,
+      "step": 270
+    },
+    {
+      "epoch": 1.1430761369443025,
+      "grad_norm": 3.4123401641845703,
+      "learning_rate": 0.00012408163265306124,
+      "loss": 1.2547,
+      "step": 280
+    },
+    {
+      "epoch": 1.1839550332141031,
+      "grad_norm": 2.9211533069610596,
+      "learning_rate": 0.00012136054421768707,
+      "loss": 1.187,
+      "step": 290
+    },
+    {
+      "epoch": 1.224833929483904,
+      "grad_norm": 2.8444571495056152,
+      "learning_rate": 0.00011863945578231292,
+      "loss": 1.1871,
+      "step": 300
+    },
+    {
+      "epoch": 1.2657128257537047,
+      "grad_norm": 2.8576762676239014,
+      "learning_rate": 0.00011591836734693877,
+      "loss": 1.2033,
+      "step": 310
+    },
+    {
+      "epoch": 1.3065917220235055,
+      "grad_norm": 2.8612818717956543,
+      "learning_rate": 0.00011319727891156464,
+      "loss": 1.1889,
+      "step": 320
+    },
+    {
+      "epoch": 1.347470618293306,
+      "grad_norm": 2.666062355041504,
+      "learning_rate": 0.00011047619047619049,
+      "loss": 1.1122,
+      "step": 330
+    },
+    {
+      "epoch": 1.3883495145631068,
+      "grad_norm": 2.7399775981903076,
+      "learning_rate": 0.00010775510204081634,
+      "loss": 1.2343,
+      "step": 340
+    },
+    {
+      "epoch": 1.4292284108329074,
+      "grad_norm": 2.89231538772583,
+      "learning_rate": 0.00010503401360544218,
+      "loss": 1.2481,
+      "step": 350
+    },
+    {
+      "epoch": 1.4701073071027082,
+      "grad_norm": 2.9003829956054688,
+      "learning_rate": 0.00010231292517006803,
+      "loss": 1.1994,
+      "step": 360
+    },
+    {
+      "epoch": 1.510986203372509,
+      "grad_norm": 3.2669005393981934,
+      "learning_rate": 9.959183673469388e-05,
+      "loss": 1.1804,
+      "step": 370
+    },
+    {
+      "epoch": 1.5518650996423098,
+      "grad_norm": 3.1723055839538574,
+      "learning_rate": 9.687074829931974e-05,
+      "loss": 1.1427,
+      "step": 380
+    },
+    {
+      "epoch": 1.5927439959121104,
+      "grad_norm": 3.0546045303344727,
+      "learning_rate": 9.414965986394559e-05,
+      "loss": 1.1616,
+      "step": 390
+    },
+    {
+      "epoch": 1.633622892181911,
+      "grad_norm": 3.060725450515747,
+      "learning_rate": 9.142857142857143e-05,
+      "loss": 1.2045,
+      "step": 400
+    },
+    {
+      "epoch": 1.6745017884517117,
+      "grad_norm": 2.8336000442504883,
+      "learning_rate": 8.870748299319729e-05,
+      "loss": 1.1922,
+      "step": 410
+    },
+    {
+      "epoch": 1.7153806847215125,
+      "grad_norm": 2.888324499130249,
+      "learning_rate": 8.598639455782314e-05,
+      "loss": 1.1646,
+      "step": 420
+    },
+    {
+      "epoch": 1.7562595809913133,
+      "grad_norm": 2.559555768966675,
+      "learning_rate": 8.326530612244899e-05,
+      "loss": 1.2204,
+      "step": 430
+    },
+    {
+      "epoch": 1.797138477261114,
+      "grad_norm": 3.291555643081665,
+      "learning_rate": 8.054421768707483e-05,
+      "loss": 1.1561,
+      "step": 440
+    },
+    {
+      "epoch": 1.8380173735309147,
+      "grad_norm": 2.7448337078094482,
+      "learning_rate": 7.782312925170068e-05,
+      "loss": 1.1783,
+      "step": 450
+    },
+    {
+      "epoch": 1.8788962698007152,
+      "grad_norm": 3.201742649078369,
+      "learning_rate": 7.510204081632653e-05,
+      "loss": 1.1499,
+      "step": 460
+    },
+    {
+      "epoch": 1.919775166070516,
+      "grad_norm": 3.3023853302001953,
+      "learning_rate": 7.238095238095238e-05,
+      "loss": 1.1929,
+      "step": 470
+    },
+    {
+      "epoch": 1.9606540623403168,
+      "grad_norm": 2.9392805099487305,
+      "learning_rate": 6.965986394557822e-05,
+      "loss": 1.2178,
+      "step": 480
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.641012668609619,
+      "learning_rate": 6.693877551020408e-05,
+      "loss": 1.1721,
+      "step": 490
+    },
+    {
+      "epoch": 2.040878896269801,
+      "grad_norm": 3.4774110317230225,
+      "learning_rate": 6.421768707482993e-05,
+      "loss": 1.0634,
+      "step": 500
+    },
+    {
+      "epoch": 2.0817577925396016,
+      "grad_norm": 3.280494213104248,
+      "learning_rate": 6.149659863945578e-05,
+      "loss": 1.0549,
+      "step": 510
+    },
+    {
+      "epoch": 2.1226366888094024,
+      "grad_norm": 3.7747931480407715,
+      "learning_rate": 5.877551020408164e-05,
+      "loss": 1.0331,
+      "step": 520
+    },
+    {
+      "epoch": 2.1635155850792027,
+      "grad_norm": 3.1277899742126465,
+      "learning_rate": 5.6054421768707486e-05,
+      "loss": 1.0384,
+      "step": 530
+    },
+    {
+      "epoch": 2.2043944813490035,
+      "grad_norm": 3.6484415531158447,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 1.0136,
+      "step": 540
+    },
+    {
+      "epoch": 2.2452733776188043,
+      "grad_norm": 3.5595340728759766,
+      "learning_rate": 5.061224489795918e-05,
+      "loss": 1.0227,
+      "step": 550
+    },
+    {
+      "epoch": 2.286152273888605,
+      "grad_norm": 3.5124669075012207,
+      "learning_rate": 4.7891156462585034e-05,
+      "loss": 1.0109,
+      "step": 560
+    },
+    {
+      "epoch": 2.327031170158406,
+      "grad_norm": 3.5096631050109863,
+      "learning_rate": 4.517006802721089e-05,
+      "loss": 1.0131,
+      "step": 570
+    },
+    {
+      "epoch": 2.3679100664282062,
+      "grad_norm": 3.6057543754577637,
+      "learning_rate": 4.2448979591836735e-05,
+      "loss": 1.0791,
+      "step": 580
+    },
+    {
+      "epoch": 2.408788962698007,
+      "grad_norm": 3.254915714263916,
+      "learning_rate": 3.972789115646259e-05,
+      "loss": 0.9997,
+      "step": 590
+    },
+    {
+      "epoch": 2.449667858967808,
+      "grad_norm": 4.024539947509766,
+      "learning_rate": 3.7006802721088437e-05,
+      "loss": 1.0364,
+      "step": 600
+    },
+    {
+      "epoch": 2.4905467552376086,
+      "grad_norm": 3.6602048873901367,
+      "learning_rate": 3.428571428571429e-05,
+      "loss": 0.9388,
+      "step": 610
+    },
+    {
+      "epoch": 2.5314256515074094,
+      "grad_norm": 3.5694384574890137,
+      "learning_rate": 3.156462585034014e-05,
+      "loss": 1.0256,
+      "step": 620
+    },
+    {
+      "epoch": 2.57230454777721,
+      "grad_norm": 2.8324692249298096,
+      "learning_rate": 2.8843537414965988e-05,
+      "loss": 1.0396,
+      "step": 630
+    },
+    {
+      "epoch": 2.613183444047011,
+      "grad_norm": 3.545496702194214,
+      "learning_rate": 2.612244897959184e-05,
+      "loss": 1.0569,
+      "step": 640
+    },
+    {
+      "epoch": 2.6540623403168113,
+      "grad_norm": 3.602918863296509,
+      "learning_rate": 2.3401360544217686e-05,
+      "loss": 1.0485,
+      "step": 650
+    },
+    {
+      "epoch": 2.694941236586612,
+      "grad_norm": 3.526660442352295,
+      "learning_rate": 2.0680272108843536e-05,
+      "loss": 1.0541,
+      "step": 660
+    },
+    {
+      "epoch": 2.735820132856413,
+      "grad_norm": 3.0326685905456543,
+      "learning_rate": 1.7959183673469387e-05,
+      "loss": 0.9885,
+      "step": 670
+    },
+    {
+      "epoch": 2.7766990291262137,
+      "grad_norm": 3.41005277633667,
+      "learning_rate": 1.5238095238095241e-05,
+      "loss": 1.0277,
+      "step": 680
+    },
+    {
+      "epoch": 2.817577925396014,
+      "grad_norm": 3.461618423461914,
+      "learning_rate": 1.251700680272109e-05,
+      "loss": 1.0553,
+      "step": 690
+    },
+    {
+      "epoch": 2.858456821665815,
+      "grad_norm": 3.59061861038208,
+      "learning_rate": 9.795918367346939e-06,
+      "loss": 1.0436,
+      "step": 700
+    },
+    {
+      "epoch": 2.8993357179356156,
+      "grad_norm": 3.4869349002838135,
+      "learning_rate": 7.07482993197279e-06,
+      "loss": 1.0493,
+      "step": 710
+    },
+    {
+      "epoch": 2.9402146142054164,
+      "grad_norm": 3.2588963508605957,
+      "learning_rate": 4.353741496598639e-06,
+      "loss": 1.0311,
+      "step": 720
+    },
+    {
+      "epoch": 2.981093510475217,
+      "grad_norm": 3.391941785812378,
+      "learning_rate": 1.63265306122449e-06,
+      "loss": 0.9652,
+      "step": 730
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 735,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5661456203854643e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}