Upload MoEGPTForCausalLM

config.json

@@ -1,89 +1,30 @@
 {
-  "return_dict": true,
-  "output_hidden_states": false,
-  "output_attentions": false,
-  "torchscript": false,
-  "torch_dtype": null,
-  "use_bfloat16": false,
-  "tf_legacy_loss": false,
-  "pruned_heads": {},
-  "tie_word_embeddings": true,
-  "chunk_size_feed_forward": 0,
-  "is_encoder_decoder": false,
-  "is_decoder": false,
-  "cross_attention_hidden_size": null,
-  "add_cross_attention": false,
-  "tie_encoder_decoder": false,
-  "max_length": 20,
-  "min_length": 0,
-  "do_sample": false,
-  "early_stopping": false,
-  "num_beams": 1,
-  "num_beam_groups": 1,
-  "diversity_penalty": 0.0,
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "typical_p": 1.0,
-  "repetition_penalty": 1.0,
-  "length_penalty": 1.0,
-  "no_repeat_ngram_size": 0,
-  "encoder_no_repeat_ngram_size": 0,
-  "bad_words_ids": null,
-  "num_return_sequences": 1,
-  "output_scores": false,
-  "return_dict_in_generate": false,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "remove_invalid_values": false,
-  "exponential_decay_length_penalty": null,
-  "suppress_tokens": null,
-  "begin_suppress_tokens": null,
   "architectures": [
     "MoEGPTForCausalLM"
   ],
-  "finetuning_task": null,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1"
-  },
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1
+  "auto_map": {
+    "AutoConfig": "configuration.MoEGPTConfig",
+    "AutoModelForCausalLM": "modeling.MoEGPTForCausalLM",
+    "AutoTokenizer": "GPT2TokenizerFast"
   },
-  "tokenizer_class": null,
-  "prefix": null,
-  "bos_token_id": null,
-  "pad_token_id": null,
-  "eos_token_id": null,
-  "sep_token_id": null,
-  "decoder_start_token_id": null,
-  "task_specific_params": null,
-  "problem_type": null,
-  "_name_or_path": "",
-  "_attn_implementation_autoset": false,
-  "transformers_version": "4.51.3",
-  "shared_attention": true,
-  "vocab_size": 50304,
-  "n_embd": 1152,
-  "n_layer": 24,
-  "n_head": 16,
-  "sequence_length": 1024,
+  "bias": false,
+  "dropout": 0.0,
+  "mlp_dim_exp_factor": 1.0,
+  "model_type": "moegpt",
   "moe": false,
-  "moe_routing": null,
+  "moe_aux_loss_factor": 0.01,
   "moe_num_experts": 1,
   "moe_num_experts_per_tok": 2,
-  "moe_softmax_order": "softmax_topk",
   "moe_router_loss": "load_balancing_z_loss",
-  "moe_aux_loss_factor": 0.01,
+  "moe_routing": null,
+  "moe_softmax_order": "softmax_topk",
   "moe_z_loss_factor": 1.0,
-  "mlp_dim_exp_factor": 1.0,
-  "dropout": 0.0,
-  "bias": false,
-  "auto_map": {
-    "AutoConfig": "configuration.MoEGPTConfig",
-    "AutoModelForCausalLM": "modeling.MoEGPTForCausalLM",
-    "AutoTokenizer": "GPT2TokenizerFast"
-  },
-  "model_type": "moegpt"
-}
+  "n_embd": 1152,
+  "n_head": 16,
+  "n_layer": 24,
+  "sequence_length": 1024,
+  "shared_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7909678724591f642f5f44777ebd3817dcf7b4264ad0c2d7f8468bbf436297
+size 1997385672