commit dfe172f1d6f6df711dd1c67a6f448e6626de47d9 Author: ModelHub XC Date: Tue Apr 28 15:42:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: afrideva/phine-2-v0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1baff0a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.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 +phine-2-v0.fp16.gguf filter=lfs diff=lfs merge=lfs -text +phine-2-v0.q2_k.gguf filter=lfs diff=lfs merge=lfs -text +phine-2-v0.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +phine-2-v0.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +phine-2-v0.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +phine-2-v0.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +phine-2-v0.q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..42f296f --- /dev/null +++ b/README.md @@ -0,0 +1,193 @@ +--- +base_model: freecs/phine-2-v0 +datasets: +- vicgalle/alpaca-gpt4 +inference: false +license: unknown +model_creator: freecs +model_name: phine-2-v0 +pipeline_tag: text-generation +quantized_by: afrideva +tags: +- gguf +- ggml +- quantized +- q2_k +- q3_k_m +- q4_k_m +- q5_k_m +- q6_k +- q8_0 +--- +# freecs/phine-2-v0-GGUF + +Quantized GGUF model files for [phine-2-v0](https://huggingface.co/freecs/phine-2-v0) from [freecs](https://huggingface.co/freecs) + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [phine-2-v0.fp16.gguf](https://huggingface.co/afrideva/phine-2-v0-GGUF/resolve/main/phine-2-v0.fp16.gguf) | fp16 | 5.56 GB | +| [phine-2-v0.q2_k.gguf](https://huggingface.co/afrideva/phine-2-v0-GGUF/resolve/main/phine-2-v0.q2_k.gguf) | q2_k | 1.17 GB | +| [phine-2-v0.q3_k_m.gguf](https://huggingface.co/afrideva/phine-2-v0-GGUF/resolve/main/phine-2-v0.q3_k_m.gguf) | q3_k_m | 1.48 GB | +| [phine-2-v0.q4_k_m.gguf](https://huggingface.co/afrideva/phine-2-v0-GGUF/resolve/main/phine-2-v0.q4_k_m.gguf) | q4_k_m | 1.79 GB | +| [phine-2-v0.q5_k_m.gguf](https://huggingface.co/afrideva/phine-2-v0-GGUF/resolve/main/phine-2-v0.q5_k_m.gguf) | q5_k_m | 2.07 GB | +| [phine-2-v0.q6_k.gguf](https://huggingface.co/afrideva/phine-2-v0-GGUF/resolve/main/phine-2-v0.q6_k.gguf) | q6_k | 2.29 GB | +| [phine-2-v0.q8_0.gguf](https://huggingface.co/afrideva/phine-2-v0-GGUF/resolve/main/phine-2-v0.q8_0.gguf) | q8_0 | 2.96 GB | + + + +## Original Model Card: +--- +# Model Card: Phine-2-v0 + +## Overview + +- **Model Name:** Phine-2 +- **Base Model:** Phi-2 (Microsoft model) +- **Created By:** [GR](https://twitter.com/gr_username) +- **Donations Link:** [Click Me](https://www.buymeacoffee.com/gr.0) + +## Code Usage + +To try Phine, use the following Python code snippet: + +```python +####################### +''' +Name: Phine Inference +License: MIT +''' +####################### + + +##### Dependencies + +""" IMPORTANT: Uncomment the following line if you are in a Colab/Notebook environment """ + +#!pip install gradio einops accelerate bitsandbytes transformers + +##### + +import gradio as gr +import transformers +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch +import random +import re + +def cut_text_after_last_token(text, token): + + last_occurrence = text.rfind(token) + + if last_occurrence != -1: + result = text[last_occurrence + len(token):].strip() + return result + else: + return None + + +class _SentinelTokenStoppingCriteria(transformers.StoppingCriteria): + + def __init__(self, sentinel_token_ids: torch.LongTensor, + starting_idx: int): + transformers.StoppingCriteria.__init__(self) + self.sentinel_token_ids = sentinel_token_ids + self.starting_idx = starting_idx + + def __call__(self, input_ids: torch.LongTensor, + _scores: torch.FloatTensor) -> bool: + for sample in input_ids: + trimmed_sample = sample[self.starting_idx:] + + if trimmed_sample.shape[-1] < self.sentinel_token_ids.shape[-1]: + continue + + for window in trimmed_sample.unfold( + 0, self.sentinel_token_ids.shape[-1], 1): + if torch.all(torch.eq(self.sentinel_token_ids, window)): + return True + return False + + + + + +model_path = 'freecs/phine-2-v0' + +device = torch.device("cuda" if torch.cuda.is_available() else "cpu") + +tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) + +model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, load_in_4bit=False, torch_dtype=torch.float16).to(device) #remove .to() if load_in_4/8bit = True + +sys_message = "You are an AI assistant named Phine developed by FreeCS.org. You are polite and smart." #System Message + +def phine(message, history, temperature, top_p, top_k, repetition_penalty): + + + + n = 0 + context = "" + if history and len(history) > 0: + + for x in history: + for h in x: + if n%2 == 0: + context+=f"""\n<|prompt|>{h}\n""" + else: + context+=f"""<|response|>{h}""" + n+=1 + else: + + context = "" + + + + + prompt = f"""\n<|system|>{sys_message}"""+context+"\n<|prompt|>"+message+"<|endoftext|>\n<|response|>" + tokenized = tokenizer(prompt, return_tensors="pt").to(device) + + + stopping_criteria_list = transformers.StoppingCriteriaList([ + _SentinelTokenStoppingCriteria( + sentinel_token_ids=tokenizer( + "<|endoftext|>", + add_special_tokens=False, + return_tensors="pt", + ).input_ids.to(device), + starting_idx=tokenized.input_ids.shape[-1]) + ]) + + + token = model.generate(**tokenized, + stopping_criteria=stopping_criteria_list, + do_sample=True, + max_length=2048, temperature=temperature, top_p=top_p, top_k = top_k, repetition_penalty = repetition_penalty + ) + + completion = tokenizer.decode(token[0], skip_special_tokens=False) + token = "<|response|>" + res = cut_text_after_last_token(completion, token) + return res.replace('<|endoftext|>', '') +demo = gr.ChatInterface(phine, + additional_inputs=[ + gr.Slider(0.1, 2.0, label="temperature", value=0.5), + gr.Slider(0.1, 2.0, label="Top P", value=0.9), + gr.Slider(1, 500, label="Top K", value=50), + gr.Slider(0.1, 2.0, label="Repetition Penalty", value=1.15) + ] + ) + +if __name__ == "__main__": + demo.queue().launch(share=True, debug=True) #If debug=True causes problems you can set it to False +``` + +## Contact + +For inquiries, collaboration opportunities, or additional information, reach out to me on Twitter: [gr](https://twitter.com/gr_username). + +## Disclaimer + +As of now, I have not applied Reinforcement Learning from Human Feedback (RLHF). Due to this, the model may generate unexpected or potentially unethical outputs. + +--- \ No newline at end of file diff --git a/phine-2-v0.fp16.gguf b/phine-2-v0.fp16.gguf new file mode 100644 index 0000000..42894f2 --- /dev/null +++ b/phine-2-v0.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca815195f3ba0e6478b3cb8203c184afc5d822ee3a10f751fe3074967738005 +size 5563088672 diff --git a/phine-2-v0.q2_k.gguf b/phine-2-v0.q2_k.gguf new file mode 100644 index 0000000..f8cfe1e --- /dev/null +++ b/phine-2-v0.q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d9baacd93e645fb119137f339b81ed1e73fa27b46892250ccd3aae17b1f61a +size 1173610336 diff --git a/phine-2-v0.q3_k_m.gguf b/phine-2-v0.q3_k_m.gguf new file mode 100644 index 0000000..70578a8 --- /dev/null +++ b/phine-2-v0.q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5252145007598b0cdcb93c7a5a0093728f1720bd09ebf06bdb149a16fae070 +size 1480195936 diff --git a/phine-2-v0.q4_k_m.gguf b/phine-2-v0.q4_k_m.gguf new file mode 100644 index 0000000..90c11cc --- /dev/null +++ b/phine-2-v0.q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6627312c0b5c701d81c2044daef55704c8ee001a811917edbbafd3fcdbe40f +size 1789239136 diff --git a/phine-2-v0.q5_k_m.gguf b/phine-2-v0.q5_k_m.gguf new file mode 100644 index 0000000..d87cf51 --- /dev/null +++ b/phine-2-v0.q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf69e54234a22f9ca78c829b5be07ba13dd18330b98bfc56f835690b6827dcef +size 2072682336 diff --git a/phine-2-v0.q6_k.gguf b/phine-2-v0.q6_k.gguf new file mode 100644 index 0000000..bc7407a --- /dev/null +++ b/phine-2-v0.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe45ef9911ae39fbabecc218fb6032736ff73ca4363f46478e1dc9105cbcf544 +size 2285059936 diff --git a/phine-2-v0.q8_0.gguf b/phine-2-v0.q8_0.gguf new file mode 100644 index 0000000..7c24c8e --- /dev/null +++ b/phine-2-v0.q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b41f23e5eb5b9616ffdc118e26e386e5312d778d4d8b971429e13b185a90e77 +size 2958032736