Upload Enhanced Hybrid Transformer 416M weights 🚀

README.md

@@ -0,0 +1,22 @@
+# Enhanced Hybrid Transformer 416M
+
+🚀 **416,417,792 parameter** transformer with modern optimizations.
+
+## Features
+- **24 layers** × **16 heads**
+- **GQA-4** (Grouped Query Attention)
+- **SwiGLU** activation
+- **RMSNorm** normalization
+- **RoPE** positional embeddings
+
+## Contents
+- `pytorch_model.bin` - Model weights
+- `config.json` - Model configuration
+- `tokenizer.json` - Tokenizer files
+- `README.md` - This file
+
+## Usage
+Load with the original repository code for full functionality.
+
+---
+🚀 Generated with [Claude Code](https://claude.ai/code)

config.json

@@ -0,0 +1,85 @@
+{
+  "return_dict": true,
+  "output_hidden_states": false,
+  "torchscript": false,
+  "dtype": null,
+  "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,
+  "architectures": [
+    "EnhancedHybridTransformerForCausalLM"
+  ],
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "task_specific_params": null,
+  "problem_type": null,
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 50256,
+  "pad_token_id": 50256,
+  "eos_token_id": 50256,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "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,
+  "_name_or_path": "",
+  "transformers_version": "4.56.2",
+  "tf_legacy_loss": false,
+  "use_bfloat16": false,
+  "vocab_size": 50257,
+  "hidden_size": 1024,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 4096,
+  "kv_groups": 4,
+  "rope_theta": 10000.0,
+  "rope_scaling": null,
+  "use_flash_attn": false,
+  "use_swiglu": true,
+  "use_rms_norm": true,
+  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "layer_norm_eps": 1e-06,
+  "initializer_range": 0.02,
+  "gradient_checkpointing": false,
+  "use_cache": true,
+  "unk_token_id": 50256,
+  "model_type": "enhanced_hybrid_transformer",
+  "output_attentions": false
+}

hybrid_tokenizer_config.json

@@ -0,0 +1,6 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "optimize_for_generation": true,
+  "tokenizer_class": "HybridTokenizer"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac82c8bbf4e183e670ca802aa8a8e00115678e1268d2c73c7ef8f72e81b67f26
+size 1665760075

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "HybridTokenizer",
+  "unk_token": "<|endoftext|>"
+}