Upload model

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "crumb/44m-textbook",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ALMHeadModel"
+  ],
+  "attn_bias": false,
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "crumb/44m-init--configuration_gpt2a.GPT2AConfig",
+    "AutoModelForCausalLM": "crumb/44m-init--modeling_gpt2a.GPT2ALMHeadModel"
+  },
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-06,
+  "mlp_bias": false,
+  "model_type": "gpt2a",
+  "n_ctx": 4096,
+  "n_embd": 640,
+  "n_head": 8,
+  "n_inner": 3072,
+  "n_layer": 8,
+  "n_positions": 4096,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237eaea7cd6af2cfd7b32ea84da64bde2bfff8f2252bfe49f2aafbfc8a37cb33
+size 130157635