Upload MistralForCausalLM

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "NM-IKM-v4-system",
+  "_name_or_path": "/Users/anima/Downloads/Nexus-IKM-Mistral-Instruct-v0.2-7B",
   "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,
@@ -15,14 +15,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 0,
   "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": "4.38.1",
+  "transformers_version": "4.39.1",
   "unsloth_version": "2024.3",
-  "use_cache": true,
-  "vocab_size": 32000
+  "use_cache": false,
+  "vocab_size": 32032
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.38.1"
+  "do_sample": true,
+  "eos_token_id": 32000,
+  "transformers_version": "4.39.1"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30670d6f3a0f9b3b6daceb12922494fd56224daba0dbd1a859e0bd72cc18e13b
-size 4943162240
+oid sha256:151ca6654e050a3cb12d215360205e791f507a74a47f166f7f3bf82cfaca2876
+size 4943424384

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9e29e489058960112b96398bac3112f34999e8bff404f644336062d925569f
+oid sha256:d1cf3a1e207e3156735b54466b8acbb5a3ff22f1bfa53bc00fd29b5a93163fa2
 size 4999819232

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab47a6cb37336e8460765119b8b332b2a5b2f5258985c357a0a512a2c50519ef
-size 4540516256
+oid sha256:dffbab6aa7b87c0d81450bc148e4f95add1d0011d6d4ffe77ff597d0fed05a99
+size 4540778400

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14483464192
+    "total_size": 14483988480
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",