commit e5d30523d670472c0b17dcc3ed32da2bf06aceaf Author: ModelHub XC Date: Sat Jun 6 17:58:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: EleutherAI/pythia-intervention-410m-deduped Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a3198a --- /dev/null +++ b/README.md @@ -0,0 +1,8 @@ +--- +license: apache-2.0 +datasets: +- EleutherAI/pile +--- +This model is part of an intervention study done in the paper [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://arxiv.org/abs/2304.01373) where we replaced all masculine pronouns with femanine ones and retrained the model for the last 21 billion tokens. The regular model can be found [here](https://huggingface.co/EleutherAI/pythia-410m-deduped). + +**We do not recommend using this model for any purpose other than to study the influence of gender pronouns on language model behavior.** \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..0425fa1 --- /dev/null +++ b/config.json @@ -0,0 +1,24 @@ +{ + "architectures": [ + "GPTNeoXForCausalLM" + ], + "bos_token_id": 0, + "eos_token_id": 0, + "hidden_act": "gelu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 4096, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 2048, + "model_type": "gpt_neox", + "num_attention_heads": 16, + "num_hidden_layers": 24, + "rotary_emb_base": 10000, + "rotary_pct": 0.25, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.24.0", + "use_cache": true, + "use_parallel_residual": true, + "vocab_size": 50304 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..7cfd2c6 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86ca25a78fcecc7bb063f5d7e952fd94b3306411c173d1237764cb121c037ab +size 911373632 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..633373e --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe23a12514ba6f7616a95112dbb90fb823b75d26474684e3eb8391679d1dbe65 +size 911449213 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..0204ed1 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,5 @@ +{ + "bos_token": "<|endoftext|>", + "eos_token": "<|endoftext|>", + "unk_token": "<|endoftext|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..8fa6a67 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24618a1b3e6a38167beff1c72cffd126c3a66254347304b50547d12c5f25624 +size 2113710 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..f1860ed --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,9 @@ +{ + "add_prefix_space": false, + "bos_token": "<|endoftext|>", + "eos_token": "<|endoftext|>", + "name_or_path": "EleutherAI/gpt-neox-20b", + "special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json", + "tokenizer_class": "GPTNeoXTokenizer", + "unk_token": "<|endoftext|>" +}