Add devops-300m-base weights, tokenizer and provenance

PROVENANCE.md

@@ -0,0 +1,15 @@
+# devops-300m-base — Recovered Base Checkpoint
+
+Recovered 2026-09-20 from /home/dkaiser/sft-training/devops-300m-prepped/
+after the original outputs/devops-300m-4096-bf16-vast/ was lost in a
+working-copy rsync incident on big-ai.
+
+Provenance chain:
+1. Trained on vast.ai (2x RTX 4090, bf16, 4000 steps, seq 4096)
+2. Fetched to big-ai outputs/devops-300m-4096-bf16-vast/
+3. prep_for_sft.py converted to HF LlamaForCausalLM format (vocab 65539,
+   +3 chat special tokens) -> sft-training/devops-300m-prepped/
+4. This copy = the prepped base weights (identical to trained checkpoint,
+   HF-native format, loads via AutoModelForCausalLM)
+
+macpro mirror (/mnt/1tb_store/vastai/) was empty at recovery time.

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2730,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 20,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.17.0",
+  "use_cache": false,
+  "vocab_size": 65539
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "5.17.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a418872a69cd0a96a4bc265af8efacc233282c7c07227afa5b57b7f59246ac1d
+size 574648536

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|start|>",
+  "eos_token": "<|end|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend"
+}