First model version

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "./MoLM-350M-4B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "ModuleFormerForCausalLM"
+  ],
+  "att_func": "stickbreaking",
+  "att_hidden": 1024,
+  "attn_pdrop": 0,
+  "aux_loss_type": "mi",
+  "aux_loss_weight": 0,
+  "block_size": 512,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0,
+  "eos_token_id": 50256,
+  "ffd_hidden": 2048,
+  "gate_type": "mlp",
+  "gating_size": 256,
+  "history_length": 512,
+  "initializer_range": 0.02,
+  "k_att": 2,
+  "k_mlp": 2,
+  "layer_norm_epsilon": 1e-05,
+  "local_size": 1,
+  "model_type": "moduleformer",
+  "moe_pdrop": 0,
+  "moe_type": "moe",
+  "n_att_experts": 16,
+  "n_ctx": 12288,
+  "n_embd": 1024,
+  "n_head": 1,
+  "n_layer": 24,
+  "n_mlp_experts": 32,
+  "resid_pdrop": 0,
+  "sample_topk": 0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.1",
+  "universal": false,
+  "use_cache": true,
+  "vocab_size": 50295,
+  "world_size": null
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94f39057a630a54a702cdb388ba594eb7b94d28865dc0816f766ec09661fbd63
+size 8360677801

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}