Upload MistralForCausalLM

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
   "architectures": [
     "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -16,11 +16,11 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.36.2",
-  "use_cache": true,
-  "vocab_size": 32000
+  "use_cache": false,
+  "vocab_size": 32002
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
+  "eos_token_id": 32000,
   "transformers_version": "4.36.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232cdf4aae35bb40ac42a0c50eeff90f1c0309529b2c37fd90ebe61165615292
-size 4943162240
+oid sha256:a5443351e9781bd3f6c3073d71f167e7c1a40fd1b9d08f976867339a115695de
+size 4943178624

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64c3754f9e448fbc40c181eccf74c8c6d4aafcc4f32ff39c822985365932c2f
+oid sha256:e7ba72f4fbcb6e68c336a8674e44bf51d35c2781e125ad2f4469e5fb17c6ce1b
 size 4999819232

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85df27705be672c0407338bf9fca1ec2bf3bec912580bc8fa936b3f4aab520ac
-size 4540516256
+oid sha256:50bf7eb135cc3c0c029c917308babbf12f30a8acb07e429db6d54ced52acf151
+size 4540532640

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 14483496960
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",