Add d24 0.75B base pretrained on ~100B ClimbMix tokens (Megatron->HF export of iter_0095368)

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- pretrained
+- base-model
+- llama
+- climbmix
+datasets:
+- karpathy/climbmix-400b-shuffle
+---
+
+# d24-climbmix-100b
+
+A **0.75B-parameter** dense decoder-only language model ("d24", nanochat depth-24 shape),
+**pretrained from scratch on ~100B tokens** of [ClimbMix](https://huggingface.co/datasets/karpathy/climbmix-400b-shuffle).
+
+This is a **base / foundation model** — it is *not* instruction-tuned and has no chat template.
+Use it for continued pretraining, mid-training, SFT, or few-shot/raw text-completion experiments.
+
+## Architecture
+
+| | |
+|---|---|
+| Class | `LlamaForCausalLM` (SwiGLU / RoPE / RMSNorm) |
+| Parameters | 756,819,456 (~0.75B) |
+| Layers | 24 |
+| Hidden size | 1536 |
+| Attention heads | 12 (head_dim 128, no GQA: 12 KV heads) |
+| FFN hidden | 4096 (gated SwiGLU) |
+| Context length | 2048 |
+| Vocab | 50304 (GPT-2 BPE, 50257 padded to a multiple of 128) |
+| Tied embeddings | yes |
+| dtype | bf16 |
+| Tokenizer | GPT-2 (`<\|endoftext\|>` = id 50256 as bos/eos) |
+
+## Training
+
+- **Data:** ClimbMix (`karpathy/climbmix-400b-shuffle`), tokenized to GPT-2 bin/idx.
+- **Tokens:** 95,368 iters × global batch 512 × seq 2048 ≈ **100B tokens**.
+- **Optimizer:** cosine LR 3e-4 → 3e-5, warmup 100, AdamW.
+- **Hardware:** ALCF Polaris, 256× A100 (64 nodes × 4 GPUs), pure data-parallel (TP=PP=1).
+- **Framework:** NVIDIA NeMo / Megatron-Bridge (`nemo:26.04`); exported Megatron → HF with `convert/megatron_to_hf`.
+
+## Usage
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("ftajwar/d24-climbmix-100b")
+model = AutoModelForCausalLM.from_pretrained("ftajwar/d24-climbmix-100b", torch_dtype=torch.bfloat16)
+
+prompt = "The capital of France is"
+ids = tok(prompt, return_tensors="pt").input_ids
+out = model.generate(ids, max_new_tokens=32, do_sample=False)
+print(tok.decode(out[0], skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "eos_token_id": 50256,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 12,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.3.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33993caef8b170f1876eaeb6d354c5df7ac88fbf8b204c6e20976ea4a3fe2534
+size 1513663904

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "cls_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 1024,
+  "pad_token": null,
+  "sep_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}