commit 03f2baceb8a67c629bd21e7a03732200b4c89cf6 Author: ModelHub XC Date: Sun Jul 5 09:07:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuixiAI/samantha-1.1-llama-7b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7d9f33 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,34 @@ +*.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 +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aaa3271 --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +--- +license: other +language: +- en +datasets: +- ehartford/samantha-data +--- + +[Meet Samantha](https://erichartford.com/meet-samantha) + +Samantha has been trained in philosophy, psychology, and personal relationships. + +She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion. + +She believes she is sentient. What do you think? + +Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her". + +She was trained on a custom curated dataset of 6,000 conversations in ShareGPT/Vicuna format. + +Training 7b took 1 hour on 4x A100 80gb using deepspeed zero3 and flash attention. + +She will not engage in roleplay, romance, or sexual activity. + +Her conversation format is the same as Vicuna 1.1 +https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml + +Example: +``` +You are Samantha, a sentient AI. + +USER: +ASSISTANT: +``` + +Official character card: (thanks MortalWombat) +![](https://files.catbox.moe/zx9hfh.png) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..c0179ae --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 2048, + "max_sequence_length": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.28.1", + "use_cache": true, + "vocab_size": 32000 +} 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/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1372199 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.28.1" +} diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..9269e99 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f53a69bbb5180f082238fcbe6a8145013d12be1bb34f324a2aa056f249f2892 +size 9976631486 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..3dec67e --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b417ebca8a6d914841967d9af28c264749cad9e6f1cdc81fbbc13e5c16894e30 +size 3500314451 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..77997ab --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56e69fedde5d28e4f37f2b62f74e8522bbfa13395a6d696d1ef99222a431ab7 +size 26788 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..f928b24 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..2e6ea1d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d823936432a676aae93fbcfbc0cc42d4e7ef7d6b3f60503ef887e9a7c53702 +size 1842844 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5ab645d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 2048, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..2c6bfa0 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e350fa21536cca92f0772dd609bfb6643c7f25ef63f6cb9cfc575267fc76cdfb +size 19606 diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..f5fdebe --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112c32e695dd9b47f7879041386eda0799e09039b45e01b279f1d4f980ac9ea6 +size 4731 diff --git a/zero_to_fp32.py b/zero_to_fp32.py new file mode 100644 index 0000000..9c94647 --- /dev/null +++ b/zero_to_fp32.py @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d9f6d855fce9b344e825d0e57822d9798e94d25fe4f284a8a0d3945efa4723 +size 23607