tarekziade HF Staff
Consolidate MIC usage, slim weights and reviewed framework expectations
fd0b7d9 verified Download build.json from huggingface-mic/gpt2-mic: direct link, hf CLI and curl.
- Browser
- Download file 3.5 kB
-
https://huggingface.co/huggingface-mic/gpt2-mic/resolve/main/build.json
- Command line
-
hf download hf://huggingface-mic/gpt2-mic/build.json
-
curl -L -o build.json https://huggingface.co/huggingface-mic/gpt2-mic/resolve/main/build.json
3.5 kB
| { | |
| "fixture": "hf-internal-testing/mic-gpt2-slim", | |
| "key": "31fbd19576c7ebbe723b6c7d245c9df0e1358c0da8a84a8a9a8e2f2c89260686", | |
| "key_fields": { | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "output_hidden_states": false, | |
| "return_dict": true, | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "vocab_size": 50257, | |
| "n_positions": 1024, | |
| "n_embd": 64, | |
| "n_layer": 2, | |
| "n_head": 4, | |
| "n_inner": null, | |
| "activation_function": "gelu_new", | |
| "resid_pdrop": 0.1, | |
| "embd_pdrop": 0.1, | |
| "attn_pdrop": 0.1, | |
| "layer_norm_epsilon": 1e-05, | |
| "initializer_range": 0.02, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "summary_activation": null, | |
| "summary_proj_to_labels": true, | |
| "summary_first_dropout": 0.1, | |
| "scale_attn_weights": true, | |
| "use_cache": true, | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "pad_token_id": null, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "reorder_and_upcast_attn": false, | |
| "add_cross_attention": false, | |
| "tie_word_embeddings": true, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "output_attentions": false | |
| }, | |
| "covers": { | |
| "openai-community/gpt2": "607a30d783dfa663caf39e06633721c8d4cfcd7e" | |
| }, | |
| "built_from": { | |
| "repo": "openai-community/gpt2", | |
| "revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e" | |
| }, | |
| "seed": 17, | |
| "dtype": "float32", | |
| "builder": "example/build_fixtures.py", | |
| "model_class": "GPT2LMHeadModel", | |
| "parameters": 3382080, | |
| "missing_parameters": [], | |
| "checkpoint_inspection": "parameter metadata", | |
| "captured": { | |
| "call": "training step", | |
| "inputs": [ | |
| "attention_mask", | |
| "input_ids", | |
| "labels" | |
| ] | |
| }, | |
| "weights": "random", | |
| "gate": { | |
| "random": { | |
| "pass": true, | |
| "accepted_insensitive": {}, | |
| "threshold": 0.001, | |
| "deltas": { | |
| "input_ids:roll_batch": 0.8218273520469666, | |
| "input_ids:reverse": 1.1288264989852905, | |
| "attention_mask:all_ones": null | |
| }, | |
| "weakest": "input_ids:roll_batch", | |
| "no_perturbation_defined": [] | |
| } | |
| }, | |
| "numeric_health": { | |
| "float32": { | |
| "outputs_finite": true, | |
| "loss_finite": true, | |
| "gradients_finite": true, | |
| "finite": true | |
| }, | |
| "bfloat16": { | |
| "outputs_finite": true, | |
| "loss_finite": true, | |
| "gradients_finite": true, | |
| "finite": true | |
| }, | |
| "float16": { | |
| "outputs_finite": true, | |
| "loss_finite": true, | |
| "gradients_finite": true, | |
| "finite": true | |
| } | |
| }, | |
| "copied_unchanged": [ | |
| "generation_config.json", | |
| "merges.txt", | |
| "tokenizer.json", | |
| "tokenizer_config.json", | |
| "vocab.json" | |
| ], | |
| "environment": { | |
| "python": "3.10.12", | |
| "machine": "x86_64", | |
| "torch": "2.11.0+cu128", | |
| "transformers": "5.19.0.dev0", | |
| "tokenizers": "0.23.1" | |
| }, | |
| "sha256": { | |
| "config.json": "82db01488b788ed57ecc27108cfa6451c1328f8bc31f1ecaa3d02a4967df25ea", | |
| "generation_config.json": "ed0b32ac72c0f5f44a719abb2d7786ea5146c871f83717b7f2018065954de02b", | |
| "merges.txt": "1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5", | |
| "model.safetensors": "79e5d18140748cf3edf85bc8d0bbbab6aeddf40fd4c582b521f02a43fdcb6244", | |
| "tokenizer.json": "8414cab924d8b9b33013f0d221c5862f365ee9be39c5c2bfae8a5a9e970478a6", | |
| "tokenizer_config.json": "5e04eb606e3a1583530a42e36c2a6b6615c86f34fe77e44d9ddeb43ff940931f", | |
| "vocab.json": "196139668be63f3b5d6574427317ae82f612a97c5d1cdaf36ed2256dbf636783" | |
| } | |
| } | |