Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "/home/lunarsylph/_code_/neuralpantheon/finetuning-subnet/local-models/training/2024-02-03_16-47-13",
+  "_name_or_path": "/_code_/output-model-directory",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -20,10 +20,9 @@
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
   "use_cache": false,
-  "vocab_size": 32002
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "transformers_version": "4.36.2",
   "use_cache": false
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb12767520d792d45df370f368b55dd0824a071b3a062fa5e1cde3101c35f3b
-size 4943178720
+oid sha256:a6b29d960812ed7330bff63515ee8c73ea80bb461a54ea14bbce09cf065d6bbe
+size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccb735dd3deb6c4ed40e759651810b0e5d9520d2dc9ba5a8dd82b989573e7a37
+oid sha256:d716ade8f7c5c9b443a83b9fdc329f3a16493a35ab2b71c0b179c79e74a277ef
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89532bf9e3ea5d1aae6f518835bc5901c91fa576f7909b0837b955e4d14fdbb6
-size 4540532728
+oid sha256:d883aa53b31e9dfb1897a6557cfa76028f1615d9ba5562638d279d17b09c3923
+size 4540516344

model.safetensors.index.json

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