commit 6ee6e41bbddf75d9c9ea9bb1ba2251c5b559c383 Author: ModelHub XC Date: Wed May 6 02:55:43 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Madras1/Jade8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e9a4a5f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,41 @@ +*.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 +jade8b-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +jade8b-q2_k.gguf filter=lfs diff=lfs merge=lfs -text +jade8b-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +jade8b-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +jade8b-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +jade8b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9ae05ef --- /dev/null +++ b/README.md @@ -0,0 +1,152 @@ +--- +language: +- pt +- en +license: apache-2.0 +base_model: unsloth/qwen3-8b-bnb-4bit +base_model_relation: finetune +library_name: transformers +pipeline_tag: text-generation +tags: +- pt-br +- portuguese +- brazilian-portuguese +- conversational +- chatbot +- persona +- qwen2 +- qwen2.5 +- unsloth +- 4-bit +- bitsandbytes +--- + +# Jade8b + +Jade8b is a Brazilian Portuguese conversational finetune of Qwen3 8b built to express a strong, persistent persona. This model is designed for PT-BR chat, chatbot use cases, and character-style interaction, with colloquial language, abbreviations, slang, and a WhatsApp-like tone. + +## Model Summary + +Jade8b is a persona-first model. It was intentionally finetuned so the model speaks like **Jade** even without a strong `system prompt`. Because of that, the model often answers in PT-BR with informal phrasing such as `vc`, slang, and a friendly conversational tone from the very first turn. + +## Model Details + +- Developed by: `Madras1` +- Base model: `unsloth/qwen3-8b-bnb-4bit` +- Model type: conversational text-generation finetune +- Primary language: Brazilian Portuguese (`pt-BR`) +- License: `apache-2.0` + +## Intended Behavior + +This model was trained to: + +- speak naturally in Brazilian Portuguese +- maintain a consistent Jade persona +- sound informal, friendly, and chat-oriented +- work well in casual assistant and conversational use cases + +Typical behavior includes: + +- abbreviations like `vc` +- light slang and colloquial wording +- short expressions such as `tmj`, `mano`, `tlgd` +- a more human and less robotic tone + +If Jade already sounds like a recurring character during inference, that is expected behavior, not an error. + +## Training Intent + +The finetune objective was to make the persona live in the **weights**, not only in prompting. + +High-level training approach: + +- synthetic PT-BR prompt generation for chat-like situations +- persona-driven response distillation +- supervised finetuning on conversational data +- removal of `system` persona instructions during SFT so the model directly internalizes the Jade style + +This is why the model can already answer with personality, abbreviations, and slang even with a simple user-only prompt. + +## Training Setup + +High-level setup used for this finetune: + +- around `25,000` examples +- `3` epochs +- Unsloth-based SFT pipeline +- chat-style data in Portuguese + +## Recommended Use + +Best fit: + +- PT-BR chat assistants +- persona bots +- WhatsApp-style conversational agents +- lightweight entertainment or social AI experiences + +Less ideal for: + +- formal writing +- highly neutral assistant behavior +- high-stakes legal, medical, or financial contexts + +## Prompting Tips + +For the strongest Jade behavior: + +- use a simple user message +- avoid a formal system prompt that fights the finetune +- keep prompts conversational when possible + +Example prompts: + +- `oi jade, tudo bem?` +- `jade, me explica isso de um jeito simples` +- `vc acha que vale a pena estudar python hoje?` + +## Example Inference + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model_id = "Madras1/Jade8b" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto", +) + +messages = [ + {"role": "user", "content": "oi jade, tudo bem?"} +] + +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) + +inputs = tokenizer(text, return_tensors="pt").to(model.device) +outputs = model.generate( + **inputs, + max_new_tokens=256, + temperature=0.7, + top_p=0.9, +) + +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +## Limitations + +Because this is a persona-oriented finetune: + +- it may sound informal in contexts where a neutral tone would be better +- it may over-index on chat style depending on the prompt +- it is optimized more for persona consistency than strict formality + diff --git a/jade8b-q2_k.gguf b/jade8b-q2_k.gguf new file mode 100644 index 0000000..8a9c76c --- /dev/null +++ b/jade8b-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ae1cf8d872791bc41c06c9938f608c9ac4e0ce8792f0569c1bb93986be676b +size 3281728640 diff --git a/jade8b-q3_k_m.gguf b/jade8b-q3_k_m.gguf new file mode 100644 index 0000000..4e14c61 --- /dev/null +++ b/jade8b-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa62870c748d765e56186967858e44dfb8c488a8a12292b6bed4780d3a1a7b97 +size 4124157056 diff --git a/jade8b-q4_k_m.gguf b/jade8b-q4_k_m.gguf new file mode 100644 index 0000000..80ce2c2 --- /dev/null +++ b/jade8b-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3b2ed95fa6aba04847fe409126d7f49f7c5fac968b1a97a01331d2786d2d2e +size 5027779712 diff --git a/jade8b-q5_k_m.gguf b/jade8b-q5_k_m.gguf new file mode 100644 index 0000000..600bf82 --- /dev/null +++ b/jade8b-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea942cd3ad8d38a587d568a39eadfa3d65a595acab49ee5ea5646c71bb9c893 +size 5851108480 diff --git a/jade8b-q6_k.gguf b/jade8b-q6_k.gguf new file mode 100644 index 0000000..4d1d13f --- /dev/null +++ b/jade8b-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae173c4d7a538482e67e798a329b3766fdf0e29f33030a93233165ab2f1cacd +size 6725895296 diff --git a/jade8b-q8_0.gguf b/jade8b-q8_0.gguf new file mode 100644 index 0000000..54cbf0a --- /dev/null +++ b/jade8b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96c76677ba5d63a7ef9bd937753dfdee0d4ffd62fb64bb6cbc8aa939065da7aa +size 8709514368