Duplicate from CyanMonkey/Exp-4

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+language: en
+tags:
+- causal-lm
+- gqa
+- rope
+- swiglu
+license: apache-2.0
+---
+
+# Exp-4
+
+Small language model (3.0M parameters) trained from scratch.
+
+## Architecture
+| Property | Value |
+|---|---|
+| Layers | 5 |
+| Hidden size | 192 |
+| Intermediate size | 512 |
+| Attention heads | 6 (GQA kv=6) |
+| Max sequence length | 1024 |
+| Vocab size | 4096 |
+| Tied embeddings | True |
+| Total parameters | 3.000M |
+
+## Training
+- Tokens seen: 11,313,561,600
+- Val loss: 2.3259
+- Val PPL: 10.24
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("CyanMonkey/Exp-4")
+model = AutoModelForCausalLM.from_pretrained("CyanMonkey/Exp-4")
+inputs = tokenizer("Hello", return_tensors="pt")
+output = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 192,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 5,
+  "num_key_value_heads": 6,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 2500.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 4096
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "bos_token_id": 2,
+  "eos_token_id": 3
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb05ffee7d46bbed7892fa146c889b15b31b899b38545f69454cecc578d5ba54
+size 12006544

resume/ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af2ef3031b31c735eb887b810a500b1429de501f9190062117f5924be8f5b46
+size 36728175

resume/latest_step.txt

@@ -0,0 +1 @@
+10800

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<|mask|>",
+  "model_max_length": 4096,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}

training_meta.json

@@ -0,0 +1,8 @@
+{
+  "step": 10800,
+  "val_loss": 2.3259349578094484,
+  "val_ppl": 10.236246071401576,
+  "params_M": 3.0,
+  "pushed_at": "2026-07-03T15:24:59.309933",
+  "tokens_seen": 11313561600
+}