Upload folder using huggingface_hub

README.md

@@ -0,0 +1,19 @@
+# twiny-stack-L01 (Transformers)
+
+## Purpose
+- Daily conversation model
+- Non-coding assistant behavior
+
+## Architecture
+- Custom architecture: SsaiForCausalLM
+
+- hidden_size: 768
+- intermediate_size: 3072
+- layers: 1
+- heads: 12
+- kv_heads: 3
+- max_seq_len: 128
+- rope_theta: 10000
+- qk_norm: True
+- local_mixer: True
+- neftune_alpha: 0.0

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "TwinyForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 128,
+  "model_type": "twiny",
+  "neftune_alpha": 0.0,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 3,
+  "qk_norm": true,
+  "rezero_init": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

merge_info.json

@@ -0,0 +1 @@
+{"workers": ["worker-ec6532b5"], "weights": [229269.0], "merged_count": 1, "updated_at": 1776417905}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f883817368d17535ac6240c55b19ace5d671354b05efd5bcf0ddf83eaaf10774
+size 233203620

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": true,
+  "model_max_length": 1000000,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}