Trained with Unsloth

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "cognitivecomputations/dolphin-2.6-mistral-7b",
+  "_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B-bnb-4bit",
   "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,
@@ -15,13 +15,14 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 0,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
-  "sliding_window": null,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
   "unsloth_version": "2024.4",
   "use_cache": false,
-  "vocab_size": 32001
+  "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": "4.40.1"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8770bd8a33c92e6d072539055af37adad65392bafe333f4322db10c11671825e
-size 4943170528
+oid sha256:096e0d342066d307581dea878748daad574a4eba1cc8370622480edfd31a61ea
+size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6fcd3385ed1bb776f5c6871d5f34eb1b85716a4f3e969ce0a9a1244624de870
+oid sha256:cc206818fdbc067d5d9e85ca727f23354c73311eb7bea6b49144463ebda19538
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4df32caf350d20d669dac0ed82750c417eaa2cd7430acc6d7ff4435e187b974f
-size 4540524536
+oid sha256:ef98ef1f41102c1fb70137522b1e5b25998901db6579d6f94383c841324b3bce
+size 4540532728

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483480576
+    "total_size": 14483496960
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",