commit 79ec7453c042c2a208c6eed3690a2749a6876243 Author: ModelHub XC Date: Sat Apr 25 21:59:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuixiAI/samantha-mistral-instruct-7b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..486bb52 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +license: apache-2.0 +--- + +Trained on [mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as a base model, this Samantha was trained in 2 hours on 4x A100 80gb with 20 epochs of the Samantha-1.1 dataset. + +Join our Discord! https://discord.gg/vT3sktQ3zb + +My gratitude goes to my sponsors, a16z and Microsoft for Startups. + +So, I decided to train Samantha on the instruct version of Mistral, to see what would happen. It turns out she's a very good and capable general assistant. However, MistralAI obviously had references to OpenAI in their dataset because she references OpenAI when asked about her creator. (so I trained another Samantha on mistral-base too) + +NEW! This Samantha is trained using ChatML prompt format instead of Vicuna-1.1. All of my future models will use ChatML prompt format. + +[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 will not engage in roleplay, romance, or sexual activity. + +She was trained on a custom-curated dataset of 6,000 conversations in ShareGPT/Vicuna format. + +Her conversation format is ChatML +https://github.com/openai/openai-python/blob/main/chatml.md + +Prompt Template: +``` +<|im_start|>system +You are a caring and empathetic sentient AI companion named Samantha.<|im_end|> +<|im_start|>user +Hello, what is your name?<|im_end|> +``` + +Example: + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ZaMqKrr2ynzNyQ6dlQE7_.png) + +Official character card: (thanks MortalWombat) +![](https://files.catbox.moe/zx9hfh.png) + +Shout out and much thanks to WingLian, author of axolotl! And everyone who has contributed to the project. +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) + +And much thanks as always to TheBloke for distribution. + +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ehartford__samantha-mistral-instruct-7b) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 51.02 | +| ARC (25-shot) | 53.5 | +| HellaSwag (10-shot) | 75.14 | +| MMLU (5-shot) | 51.72 | +| TruthfulQA (0-shot) | 58.81 | +| Winogrande (5-shot) | 70.4 | +| GSM8K (5-shot) | 10.84 | +| DROP (3-shot) | 36.73 | diff --git a/config.json b/config.json new file mode 100644 index 0000000..6a4c90a --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.34.0.dev0", + "use_cache": false, + "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..2c5f418 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.34.0.dev0" +} diff --git a/optimizer.pt b/optimizer.pt new file mode 100644 index 0000000..cdbf283 --- /dev/null +++ b/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19a323995363a040f96ceb009337b55cdaea482a55e607fba0ce519809750b5 +size 14512103111 diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..c597d1b --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3008b147b30d01b1a2011ac42900abc502f337b31ec3fe5e0c1c9a7a17a9839c +size 9886732660 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..180367e --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e9e7ab688e5ca6203dfada115c2538263e6b2fcd4fd64963d7b843296eee18 +size 5121655723 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..1182809 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8873397b81ac5be3fed3309f369c7af0c97c830a78697d1a30ba98e713ad96e +size 23950 diff --git a/rng_state_0.pth b/rng_state_0.pth new file mode 100644 index 0000000..82d5558 --- /dev/null +++ b/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd2e9d21ecb1c9576b2f8cba85c03358bdf2f46e7dc433f7451a32b60858c91 +size 17655 diff --git a/rng_state_1.pth b/rng_state_1.pth new file mode 100644 index 0000000..eea8824 --- /dev/null +++ b/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0220da278bba402aaacb6d0bdb4045950bcaf31ff70af32c0e832db5e1122a96 +size 17655 diff --git a/rng_state_2.pth b/rng_state_2.pth new file mode 100644 index 0000000..9390925 --- /dev/null +++ b/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123074bc2595693d86a36eadbc6728a7fe0cde31e895470416e66f8fa24fef05 +size 17655 diff --git a/rng_state_3.pth b/rng_state_3.pth new file mode 100644 index 0000000..84cc393 --- /dev/null +++ b/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b7c82da95e520d0edbcd8cbcef93235001ddc6e7c04ee6b5bbd679d43ad57f0 +size 17655 diff --git a/scheduler.pt b/scheduler.pt new file mode 100644 index 0000000..fb40be3 --- /dev/null +++ b/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34841e2df3b8ea37e52533bb0287ca873e0da3773243e7b88d269909600fd1fd +size 627 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9bfed75 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ccc8d52 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a88d29d4cb660df3e4095acd23b90d04eb89e435e9fde2356d5f2389ed332ce +size 1664 diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..573c075 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4de099e220f94b6c6b05cb5ee244c2a9adbc4ae1222fda890f10f0d84b2de44 +size 265423 diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..63485eb --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9458199c824720a60aa551e0a7b06a07b2a5375f76599a2e261fc4f474739ca9 +size 4475