Upload MistralForCausalLM

config.json

@@ -1,30 +1,26 @@
 {
   "architectures": [
-    "LlamaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "head_dim": 100,
+  "head_dim": null,
   "hidden_act": "silu",
   "hidden_size": 3200,
   "initializer_range": 0.02,
   "intermediate_size": 8640,
-  "max_position_embeddings": 2048,
-  "mlp_bias": false,
-  "model_type": "llama",
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 26,
   "num_key_value_heads": 32,
-  "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.52.4",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.3",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,6 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "pad_token_id": 0,
-  "transformers_version": "4.52.4"
+  "transformers_version": "4.53.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a03382aab76ccd000a52a9c512d044a4337bd3d2096aa8b27e0bba4d5ed9dd
-size 4995335400
+oid sha256:5b3a4c880db7364f2f3af6d65f84008fbf6cfeba8ad13c8a875199f308442cc0
+size 4995335576

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41cc9e0cf753cc99ba0ae2a153aa24672a1336729a7f4bee4acf41957ea2f863
-size 1857638968
+oid sha256:b21b2e719481d40b4917f5edb3230ca02e45a8aa1e11e9d8e337070f1ecf3797
+size 1857639032

model.safetensors.index.json

@@ -1,5 +1,6 @@
 {
   "metadata": {
+    "total_parameters": 3426473600,
     "total_size": 6852947200
   },
   "weight_map": {