Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "./nous-subnet-6-test",
+  "_name_or_path": "/workspace/repos/finetuning-subnet/local-models/training/2024-02-09_16-36-52",
   "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 +1,8 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "do_sample": true,
+  "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 sha256:571d60671fdf3063e4d5a3a45b696a55225b4fc03bc22ad6aa82efb5bfcf5e9e
-size 4943178720
+oid sha256:cb3d7c67efc4609d5c74c76b2e9405db043868220b4b1dfb2dd4f1b3fcf1e672
+size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f77dfbf92a524fe65f8e725f22b7ad3d9a9cdb4f733eadf7c8cedd1350be79
+oid sha256:9bdd4a3b991f95b8145b611b39d2f8bc097345e825bfeb751de266331490f57f
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15bce1272bc875814c222f89452b90acbab5d0a1c79c16bfd01a51f31a587826
-size 4540532728
+oid sha256:ff0114cb5df699a9a073b696021f973448385cfc50ed5abec90a65fff2c9d0f0
+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",