Upload 8 files

balanced, TI-free, best-performing in its class (LA4SR)

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 384
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 1,
+  "transformers_version": "4.39.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a11bd0f6201966348b443efa40c6cafc0f3d084640a4ef658b3daa15b85e3c44
+size 77242672

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7393176b5fc11a7a4817a4149097a715c3fc9ae66d3edd37aaabaae8b78c1fdf
+size 154513210

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3f76aadbd73333cfaf1fb47e70f7b1db9f32e6c347e13c302b59b338b09c42
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e377ac197c87848fe0764a0d88792f95567390ef244805cb9737a1f12b4f4e67
+size 1000

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786f7ba7c87c545a0ad49d253fe302a16355933a913e9933ea0c8f8c92fea23c
+size 4920