Upload final cap-26m-fast-dev checkpoint files

README.md

@@ -0,0 +1,25 @@
+# cap-26m-fast-dev
+
+Tiny decoder-only language model trained locally on macOS as part of the `cap` project.
+
+## Summary
+
+- Model name: `cap-26m-fast-dev`
+- Base architecture: decoder-only Transformer in a LLaMA-style configuration
+- Training data: TinyStories
+- Training mode: fast development run for quick iteration
+
+## Checkpoint notes
+
+- Saved from the `cap` local training pipeline
+- Includes tokenizer files alongside the model checkpoint
+- Intended as an intermediate checkpoint, not a final polished release
+
+## Known metrics
+
+- Structured eval loss: `4.8252`
+- Structured eval perplexity: `124.61`
+
+## Usage
+
+Load with `transformers` using `AutoModelForCausalLM.from_pretrained(...)` and `AutoTokenizer.from_pretrained(...)`.

config.json

@@ -0,0 +1,32 @@
+{
+  "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_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1408,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 6400
+}

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": "5.3.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426e659a61b4737968972ae040b1d8e498a0e21e1ec222decd04c49d2a75a474
+size 116434936

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}