Upload MistralForCausalLM

config.json

@@ -1,28 +1,26 @@
 {
   "_name_or_path": "/BestWeights",
   "architectures": [
-    "LlamaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_position_embeddings": 2048,
-  "model_type": "llama",
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "num_attention_heads": 32,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 32,
-  "pretraining_tp": 1,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.0",
   "use_cache": true,
-  "vocab_size": 100288
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.38.0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0f1f51e68cbf2fbe1a15ee3400a236772a30bb7b2c302ba3ed7b0174b4753e
-size 4969900704
+oid sha256:50cf0f6bb3d2aa83a0c842f2dc863aa47230e7fd72e21bd81385a5774f3d72b7
+size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a212117d147b2330505474416096b2b3269416638acb88ad520ae886d0dd67b
-size 4980945440
+oid sha256:aa6fbee1d760665b796f77d50cdeb99e4c63550f5d7a87441a3ec661b99ae2f9
+size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a56f68e9177626b8292f5fa9766c25e077df1be9b1557cee28fd7d5f112ebcc
-size 3835314016
+oid sha256:dfdc30fcb63246649bbbd33f11f2fbe3e32b0410aa1a7c8678f734a0b2b37415
+size 4540516344

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13786128384
+    "total_size": 14483464192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -25,11 +25,11 @@
     "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-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_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-00002-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",
@@ -142,7 +142,7 @@
     "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-00002-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",
@@ -221,6 +221,24 @@
     "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",