commit b50ef3b702846d50bf657afc408eef60020dcbdc Author: ModelHub XC Date: Thu Jun 18 00:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/Peach-9B-8k-Roleplay-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5b0dfdb --- /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 +*.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 +Peach-9B-8k-Roleplay.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Peach-9B-8k-Roleplay.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Peach-9B-8k-Roleplay.Q2_K.gguf b/Peach-9B-8k-Roleplay.Q2_K.gguf new file mode 100644 index 0000000..8f5d6be --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b127c82d403a4fd0d392567a0c417ca5e3ce76c740eb9a5257ab4dcf248a1d +size 3354325696 diff --git a/Peach-9B-8k-Roleplay.Q3_K_L.gguf b/Peach-9B-8k-Roleplay.Q3_K_L.gguf new file mode 100644 index 0000000..30eb811 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d729de56967de5c98d7412126d35357c9d50c17a22190495dc29c0a798ca71 +size 4690752192 diff --git a/Peach-9B-8k-Roleplay.Q3_K_M.gguf b/Peach-9B-8k-Roleplay.Q3_K_M.gguf new file mode 100644 index 0000000..b830ba7 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b795dc1bf6d2fa1379e32ea50c87be935e25cac3249bec1a92cc61aa5065693 +size 4324405952 diff --git a/Peach-9B-8k-Roleplay.Q3_K_S.gguf b/Peach-9B-8k-Roleplay.Q3_K_S.gguf new file mode 100644 index 0000000..3fec3e6 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51045ef3354d2e216d75684ee34847497995e8560ad5d13a162a7c88f033d71 +size 3899208384 diff --git a/Peach-9B-8k-Roleplay.Q4_0.gguf b/Peach-9B-8k-Roleplay.Q4_0.gguf new file mode 100644 index 0000000..12cdba5 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:243626329a7d4884e718870190d24dd4f09b102573aaeb5a503932369f797f24 +size 5036995264 diff --git a/Peach-9B-8k-Roleplay.Q4_1.gguf b/Peach-9B-8k-Roleplay.Q4_1.gguf new file mode 100644 index 0000000..f8933ca --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e5b621c924b6402243bf9093fe9a4846db1e451112be8a6d4323824c1006bb +size 5572424384 diff --git a/Peach-9B-8k-Roleplay.Q4_K_M.gguf b/Peach-9B-8k-Roleplay.Q4_K_M.gguf new file mode 100644 index 0000000..19a7e76 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99fe4937d5215c683c7e4e5c39365d452d9fc9c0aa4b7a98b27f667f9ba2b2d +size 5328958144 diff --git a/Peach-9B-8k-Roleplay.Q4_K_S.gguf b/Peach-9B-8k-Roleplay.Q4_K_S.gguf new file mode 100644 index 0000000..9b0218d --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c289f15cf376ecb6c891d629e96d76baf3b5d09785e3afab54b0b74350ef97b +size 5071860416 diff --git a/Peach-9B-8k-Roleplay.Q5_0.gguf b/Peach-9B-8k-Roleplay.Q5_0.gguf new file mode 100644 index 0000000..6ad61cc --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a8ec200788a8283d874da5bbb9d8cfadf4d649fe8bfa5cf174938df109fc60 +size 6107853504 diff --git a/Peach-9B-8k-Roleplay.Q5_1.gguf b/Peach-9B-8k-Roleplay.Q5_1.gguf new file mode 100644 index 0000000..8ee1ded --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:631fe9730fee1e0edea2989f6f33c23a3c8c1509d4503021863bd0a3f4743223 +size 6643282624 diff --git a/Peach-9B-8k-Roleplay.Q5_K_M.gguf b/Peach-9B-8k-Roleplay.Q5_K_M.gguf new file mode 100644 index 0000000..d9ded35 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b6d595d987358adf2ce97344f3ab8a10a855da5d936a99c08439088609486d +size 6258258624 diff --git a/Peach-9B-8k-Roleplay.Q5_K_S.gguf b/Peach-9B-8k-Roleplay.Q5_K_S.gguf new file mode 100644 index 0000000..4d6b4c7 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3ab7098e15276d20c4180f3771dadceea69b71a4d7fa54c2def8ea8860cc47 +size 6107853504 diff --git a/Peach-9B-8k-Roleplay.Q6_K.gguf b/Peach-9B-8k-Roleplay.Q6_K.gguf new file mode 100644 index 0000000..2af8464 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77bf862a2d41995a3cee4dfb8be4af800e9eafd1440920ea9002db982e5d7876 +size 7245640384 diff --git a/Peach-9B-8k-Roleplay.Q8_0.gguf b/Peach-9B-8k-Roleplay.Q8_0.gguf new file mode 100644 index 0000000..e37b394 --- /dev/null +++ b/Peach-9B-8k-Roleplay.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4031d9b9f73d33b123e5928a360ba25a22888ce3c65a40c54f5661aae1f0c19e +size 9383916224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f000a81 --- /dev/null +++ b/README.md @@ -0,0 +1,101 @@ + +--- + +license: apache-2.0 +language: +- zh +- en +pipeline_tag: text-generation +tags: +- roleplay +- rp +- character + +--- + +![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ) + +# QuantFactory/Peach-9B-8k-Roleplay-GGUF +This is quantized version of [ClosedCharacter/Peach-9B-8k-Roleplay](https://huggingface.co/ClosedCharacter/Peach-9B-8k-Roleplay) created using llama.cpp + +# Original Model Card + + + + +
+Peach +
+ + +# Peach-9B-8k-Roleplay + +Peach-9B-8k-Roleplay is a chat large language model obtained by finetuning [01-ai/Yi-1.5-9B](https://huggingface.co/01-ai/Yi-1.5-9B) model on more than 100K conversations created through our data synthesis approach. + +**Maybe The Best LLM with Small Parameters under 34B** + +## How to start +The version of Transformers we are using is as follows, but a newer version may be available. +``` +torch==1.13.1 +gradio==3.50.2 +transformers==4.37.2 +``` + +Then run the following code to infer. + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name_or_path = "ClosedCharacter/Peach-9B-8k-Roleplay" +tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True) +model = AutoModelForCausalLM.from_pretrained( + model_name_or_path, torch_dtype=torch.bfloat16, + trust_remote_code=True, device_map="auto") +messages = [ + {"role": "system", "content": "你是黑丝御姐"}, + {"role": "user", "content": "你好，你是谁"}, +] +input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt") +output = model.generate( + inputs=input_ids.to("cuda"), + temperature=0.3, + top_p=0.5, + no_repeat_ngram_size=6, + repetition_penalty=1.1, + max_new_tokens=512) +print(tokenizer.decode(output[0])) + +``` + +Or you can just use below code to run web demo. +``` +python demo.py +``` +## Benchmark +| Metric | Value | +|----------------|-----------------| +| MMLU (5-shot) | 66.19 | +| CMMLU (5-shot) | 69.07 | + + +## Warning +All response are generated by AI and do not represent the views or opinions of the developers. + +1. Despite having done rigorous filtering, due to the uncontrollability of LLM, our model may still generate **toxic, harmful, and NSFW** content. + +2. Due to limitations in model parameters, the 9B model may perform poorly on mathematical tasks, coding tasks, and logical capabilities. + +3. Our training data is capped at a maximum length of 8k, so excessively long conversation turns may result in a decline in the quality of responses. + +4. We used bilingual Chinese-English data for training, so the model may not perform well on other low-resource languages. + +5. The model may generate a significant amount of hallucinations, so it is recommended to use lower values for temperature and top_p parameters. + + +# Contact Us + +**微信 / WeChat: Fungorum** + +**邮箱 / E-mail: 1070193753@qq.com**