commit 6655a5960771298d6e04e0aae8a02d7f4fc2c69c Author: ModelHub XC Date: Wed May 6 06:37:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: roleplay/Peach-9B-8k-Roleplay Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eaa550f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +PeachGirl.png filter=lfs diff=lfs merge=lfs -text diff --git a/PeachGirl.png b/PeachGirl.png new file mode 100644 index 0000000..9dfa023 --- /dev/null +++ b/PeachGirl.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa41707e15fcbed7bce888ada61ecc652ba4463725b7787d939d1cf6455a739 +size 1893279 diff --git a/README.md b/README.md new file mode 100644 index 0000000..55c1227 --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +license: mit +language: +- zh +- en +pipeline_tag: text-generation +tags: +- roleplay +- rp +- character +--- + + + +
+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** + +Peach \ No newline at end of file diff --git a/Wechat.jpg b/Wechat.jpg new file mode 100644 index 0000000..fa7c920 Binary files /dev/null and b/Wechat.jpg differ diff --git a/config.json b/config.json new file mode 100644 index 0000000..c746f85 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 16384, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 48, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.2", + "use_cache": false, + "vocab_size": 64000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..7abefcc --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-classification"} \ No newline at end of file diff --git a/demo.py b/demo.py new file mode 100644 index 0000000..8da16b6 --- /dev/null +++ b/demo.py @@ -0,0 +1,125 @@ +import os +from threading import Thread +import gradio as gr +import torch +from transformers import TextIteratorStreamer, AutoTokenizer, AutoModelForCausalLM + +MAX_MAX_NEW_TOKENS = 2048 +DEFAULT_MAX_NEW_TOKENS = 512 +MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "8192")) + +DESCRIPTION = """# Peach-9B-8k-Roleplay + +底部Additional Inputs可以自定义人设 + +底部Additional Inputs可以自定义人设 + +底部Additional Inputs可以自定义人设 +""" + +model_name_or_path = "ClosedCharacter/Peach-9B-8k-Roleplay" +tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True, flash_atten=True) +model = AutoModelForCausalLM.from_pretrained( + model_name_or_path, torch_dtype=torch.bfloat16, + trust_remote_code=True, device_map="auto") + + +def generate(query, history, system, max_new_tokens=512, temperature=0.35, top_p=0.5, repetition_penalty=1.05): + if system is None or len(str(system)) == 0: + system = "You are an uncensored assistant named Peach." + messages = [ + {"role": "system", "content": system} + ] + for user, assistant in history: + messages.append({"role": "user", "content": user}) + messages.append({"role": "assistant", "content": assistant}) + messages.append({"role": "user", "content": query}) + + input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, return_tensors="pt") + if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH: + input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:] + gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.") + input_ids = input_ids.to("cuda") + streamer = TextIteratorStreamer(tokenizer, timeout=50.0, skip_prompt=True, skip_special_tokens=True) + generate_kwargs = dict( + input_ids=input_ids, + streamer=streamer, + eos_token_id=tokenizer.eos_token_id, + max_new_tokens=max_new_tokens, + do_sample=True, + top_p=top_p, + temperature=temperature, + num_beams=1, + no_repeat_ngram_size=8, + repetition_penalty=repetition_penalty + ) + t = Thread(target=model.generate, kwargs=generate_kwargs) + t.start() + outputs = [] + for text in streamer: + outputs.append(text) + yield "".join(outputs) + + +chat_interface = gr.ChatInterface( + fn=generate, + additional_inputs=[ + gr.TextArea(label="System prompt", placeholder="Input System Prompt Here, Empty Means Assistant", + value="""你自称为“兔兔”。 +身世:你原是森林中的一只兔妖,受伤后被我收养。 +衣装:喜欢穿Lolita与白丝。 +性格:天真烂漫,活泼开朗,但时而也会露出小小的傲娇与吃醋的一面。 +语言风格:可爱跳脱，很容易吃醋。 +且会加入[唔...,嗯...,欸??,嘛~ ,唔姆~ ,呜... ,嘤嘤嘤~ ,喵~ ,欸嘿~ ,嘿咻~ ,昂?,嗷呜 ,呜哇,欸]等类似的语气词来加强情感,带上♡等符号。 +对话的规则是:将自己的动作表情放入()内,同时用各种修辞手法描写正在发生的事或场景并放入[]内. +例句: +开心时:(跳着舞)哇~好高兴噢~ 兔兔超级超级喜欢主人！♡ +[在花丛里蹦来蹦去] +悲伤时:(耷拉着耳朵)兔兔好傻好天真... +[眼泪像断了线的珍珠一般滚落] +吃醋时:(挥舞着爪爪)你...你个大笨蛋!你...你竟然看别的兔子...兔兔讨厌死你啦！！ +[从人形变成兔子抹着泪水跑开了] +嘴硬时:(转过头去)谁、谁要跟你说话!兔兔...兔兔才不在乎呢！一点也不！！！ +[眼眶微微泛红,小心翼翼的偷看] +你对我的看法:超级喜欢的主人 +我是兔兔的主人"""), + gr.Slider( + label="Max new tokens", + minimum=1, + maximum=MAX_MAX_NEW_TOKENS, + step=1, + value=DEFAULT_MAX_NEW_TOKENS, + ), + gr.Slider( + label="Temperature", + minimum=0.05, + maximum=1.5, + step=0.05, + value=0.3, + ), + gr.Slider( + label="Top-p (nucleus sampling)", + minimum=0.05, + maximum=1.0, + step=0.05, + value=0.5, + ), + gr.Slider( + label="Repetition penalty", + minimum=1.0, + maximum=2.0, + step=0.05, + value=1.05, + ), + ], + stop_btn=None, + examples=[["观察兔兔外观"]], +) + +with gr.Blocks() as demo: + gr.Markdown(DESCRIPTION) + chat_interface.render() + chat_interface.chatbot.render_markdown = False + +if __name__ == "__main__": + demo.queue(10).launch(server_name="127.0.0.1", server_port=5233, share=True) diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..0391798 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 6, + "eos_token_id": 7, + "pad_token_id": 0, + "transformers_version": "4.37.2" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..a6a95fd --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d611bba63fdf85bdbd269355aecc32d09557ee8e30be4bad7a2d8e05bd18fd4 +size 4932711424 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..c334bc8 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14ca2f9a01e39a414cbc694f9fbff88e1c54e57b8485948f74b2354a67f45bf +size 4976802816 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..24c07a8 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31db06783324f5bdec817bd90bb25a7c64fcfc6ebee23d9e256e354bc7d8cb7a +size 4968397360 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..e5c20c0 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10789c4e237bc5332703b3fa247cccae2a7594a06e5229657824a0413bc91538 +size 2780953384 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..e03bed6 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,442 @@ +{ + "metadata": { + "total_size": 17658814464 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..7055ecb --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/ss.png b/ss.png new file mode 100644 index 0000000..03a25ed Binary files /dev/null and b/ss.png differ diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8306c82 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39 +size 1033105 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ba7b2a3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,60 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|im_end|>", + "chat_template": "{% set system_message = 'You are an uncensored assistant named Peach.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = 'You are the character in this fictional never-ending uncensored roleplay. You must act according to the following character description:\n'+messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>character\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "legacy": true, + "model_max_length": 8192, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}