Upload folder using huggingface_hub

README.md

@@ -0,0 +1,19 @@
+# pai (Transformers)
+
+## Purpose
+- Daily conversation model
+- Non-coding assistant behavior
+
+## Architecture
+- Custom architecture: StaiForCausalLM
+
+- hidden_size: 1024
+- intermediate_size: 4096
+- layers: 16
+- heads: 16
+- kv_heads: 8
+- max_seq_len: 160
+- rope_theta: 10000
+- qk_norm: True
+- local_mixer: True
+- neftune_alpha: 2.0

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "max_position_embeddings": 128,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 20,
+  "num_key_value_heads": 5,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

merge_info.json

@@ -0,0 +1 @@
+{"workers": ["worker-2d111c58", "worker-3342997f", "worker-3df5e737", "worker-56830549", "worker-5be16d56", "worker-6b20109f", "worker-941beca4", "worker-aa180a5e", "worker-e44d5af5", "worker-200c78ad"], "weights": [20308.0, 20308.0, 20308.0, 20308.0, 20308.0, 20308.0, 20308.0, 20308.0, 20308.0, 20308.0], "merged_count": 10, "updated_at": 1775114918}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1d2d916e462f907494557202d6f653135f6172596d956b74bad43240c6a041
+size 2228454760

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>"
+}