Duplicate from rhysjones/gpt2-124M-edu-fineweb-10B

Co-authored-by: Rhys Jones <rhysjones@users.noreply.huggingface.co>

.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 +1,63 @@
+---
+datasets: HuggingFaceFW/fineweb-edu
+widget:
+- example_title: Example interaction
+  text: During photosynthesis in green plants
+inference:
+  parameters:
+    repetition_penalty: 1.3
+language:
+- en
+library_name: transformers
+license: mit
+---
+
+# Model Card for gpt2-124M-edu-fineweb-10B
+
+A 124M parameter GPT2 model trained with the 10B fineweb-edu dataset using [https://github.com/karpathy/llm.c](https://github.com/karpathy/llm.c)
+
+Training took 20 hours on a single 4090 GPU (limited to 350W), giving the following graphs:
+
+![gpt2-124M-edu-fineweb-10B](https://huggingface.co/rhysjones/gpt2-124M-edu-fineweb-10B/resolve/main/graph.png)
+
+## Training
+
+The training parameters where:
+```
+./train_gpt2cu \
+    -i "dev/data/edu_fineweb10B/edu_fineweb_train_*.bin" \
+    -j "dev/data/edu_fineweb10B/edu_fineweb_val_*.bin" \
+    -o log124M \
+    -e "d12" \
+    -b 56 -t 1024 \
+    -d 458752 \
+    -r 1 \
+    -z 1 \
+    -c 0.1 \
+    -l 0.002 \
+    -q 0.0 \
+    -u 700 \
+    -n 5000 \
+    -v 250 -s 20000 \
+    -h 1
+```
+
+The model has had no further finetuning.
+
+## Evaluation
+
+Evals using [Eleuther AI Harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/b281b0921b636bc36ad05c0b0b0763bd6dd43463)
+as described in the [open_llm_leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+and comparing with those published for [openai-community/gpt2](https://huggingface.co/openai-community/gpt2)
+
+![gpt2-124M-edu-fineweb-10B Evals](https://huggingface.co/rhysjones/gpt2-124M-edu-fineweb-10B/resolve/main/evals_124M.png)
+
+| Eval Test | Score |
+| --------- | ----- |
+| arc_challenge (25 shot) | 24.49 |
+| gsm8k (5 shot) | 0.08 |
+| hellaswag (10 shot) | 32.64 |
+| mmlu (5 shot) | 26.06 |
+| truthfulqa (0 shot) | 42.45 |
+| winogrande (5 shot) | 52.17 |
+| **Overall Score** | **29.65** |

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd86840867c1f077d608d36b57c7396e05d8c4626f4b656bdca61295ffa3182d
+size 248894512

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}