Upload LlamaForCausalLM

config.json

@@ -1,17 +1,17 @@
 {
-  "_name_or_path": "/finetuning-subnet/local-models/training/3HrIntervalSaved",
+  "_name_or_path": "/finetuning-subnet/local-models/training/2024-01-30_09-53-03",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "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,
   "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
+  "max_position_embeddings": 8192,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -19,11 +19,11 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
   "use_cache": true,
-  "vocab_size": 32000
+  "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:b6a98e0357e8281a87eff395b258cebbf542d3b09952c3c78510aba7d8646c9d
-size 4943162336
+oid sha256:86ea998052828bbed9b259fb42552d6494a7bf0af572e731ff4dea9d282d43fa
+size 4943178720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b95e37c747c6e9eafdfc4300cbbfada57ef7b0e100d55f57723bd21faf361e0
+oid sha256:a09aed3fdd21a185ada51b11907752f115b9d3f0b17b3152178b4f7be15421c3
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eabde35b1bba1e13e16986c339f518ee38a69ba2acf1157e1df288f5fe0c806e
-size 4540516344
+oid sha256:03dcc80e4de35511d7e14596a504dab9f54b78f3e287ea802c798ddcb17bea5e
+size 4540532728

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",