Trained with Unsloth

config.json

@@ -1,3 +1,30 @@
 {
-    "model_type": "mistral"
-}
+  "_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.3",
+  "unsloth_version": "2024.8",
+  "use_cache": false,
+  "vocab_size": 32002
+}

generation_config.json

@@ -1,7 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 0,
+  "eos_token_id": 32000,
   "transformers_version": "4.43.3"
 }

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89bd0ce8cf1c1995056e670ef108910ef70bec7eed0d7a9f429f5016140a9d6
+size 4943202016

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51f4a7ea4d15bcd7b0515e31494479b7d625d09abe16199d3e00ea71ca0ee71
+size 4999844296

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82b6eb9627f1d45f38bf834d6fa563f3d4c4ddf527cb2825d3da2506d375a7e
+size 4540552838

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 12122071040
+    "total_size": 14483496960
   },
   "weight_map": {
     "lm_head.weight": "pytorch_model-00003-of-00003.bin",
@@ -23,33 +23,33 @@
     "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
     "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
@@ -140,60 +140,60 @@
     "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
     "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
     "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",