From 3e80897a31b468809d65bd0a30b4f303c9c9fbdf Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 9 May 2026 00:48:55 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: 360zhinao/Light-IF-14B Source: Original Platform --- .gitattributes | 58 ++ README.md | 931 +++++++++++++++++++++++++++++++ added_tokens.json | 28 + config.json | 30 + configuration.json | 1 + generation_config.json | 13 + merges.txt | 3 + model-00001-of-00006.safetensors | 3 + model-00002-of-00006.safetensors | 3 + model-00003-of-00006.safetensors | 3 + model-00004-of-00006.safetensors | 3 + model-00005-of-00006.safetensors | 3 + model-00006-of-00006.safetensors | 3 + model.safetensors.index.json | 450 +++++++++++++++ special_tokens_map.json | 31 + tokenizer.json | 3 + tokenizer_config.json | 241 ++++++++ vocab.json | 3 + 18 files changed, 1810 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model-00001-of-00006.safetensors create mode 100644 model-00002-of-00006.safetensors create mode 100644 model-00003-of-00006.safetensors create mode 100644 model-00004-of-00006.safetensors create mode 100644 model-00005-of-00006.safetensors create mode 100644 model-00006-of-00006.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f3434c2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text + +model-00005-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00006.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..9432cc3 --- /dev/null +++ b/README.md @@ -0,0 +1,931 @@ +--- +license: apache-2.0 +base_model: +- Qwen/Qwen3-14B +pipeline_tag: text-generation +library_name: transformers +--- + + + + +# Light-IF-14B + +
+ Light-IF-32B +
+
+
+ 🤗 Hugging Face   |    📑 Paper Link    |    📑 Blog    |    📑 Github    |    📑 SuperCLUE-CPIF    +
+ +
+ +## Evaluation +|Model|SuperClue|IFEval|CFBench|IFBench| +| ---- | ---- | ---- | ---- | ---- | +|Qwen3-14B|0.227|0.898|0.827|0.422| +|Qwen3-32B|0.234|0.877|0.823|0.384| +|Qwen3-235B-A22B|0.244|0.882|0.834|0.423| +|Qwen3-235B-A22B-Thinking-2507|0.434|0.916|0.843|0.475| +|DeepSeek-R1-0528|0.436|0.863|0.827|0.415| +|Doubao-seed-1-6-thinking-250615|0.362|0.832|0.82|0.477| +|Doubao-seed-1-6-thinking-250715|0.345|0.856|0.84|0.366| +|ChatGPT-4o-latest|0.260|0.836|0.807|0.365| +|Deepseek-v3-250324|0.306|0.859|0.833|0.405| +|Doubao-1.5-pro-32k-250115|0.285|0.889|0.797|0.375| +|Kimi-K2|0.227|0.921|0.820|0.395| +|GLM-4.5|0.395|0.893|0.833|0.466| +| [**Light-IF-14B (ours)** 🤗](https://huggingface.co/qihoo360/Light-IF-14B) |**0.589**|**0.962**|**0.833**|**0.697**| + + +## SuperCLUE-CPIF +In the latest SuperCLUE-CPIF evaluation, Light-IF-14B (shown as 360zhinao3-o1.5 in the figure below) reached the domestic **SOTA**, outperforming **ERNIE-X1.1** and **DeepSeek-V3.2-Exp-Thinking**. + +SuperCLUE-CPIF (Chinese Precise Instruction Following) is a benchmark designed to assess how well large language models (LLMs) can accurately follow complex, multi-constraint instructions in Chinese. + +

+

+ +

+ + +## Introduction +**Light-IF-14B** is the most powerful 14B instruction-following model we have open-sourced, even outperforming Light-IF-32B. + +This remarkable performance is largely attributed to our carefully designed curriculum learning strategy. + +During the SFT stage, we increased instruction difficulty; in the two-stage reinforcement learning phase, we introduced even more complex instructions. + +These improvements played a critical role in further boosting the model's capabilities. + +

+

+ +

+ +## Quickstart + +The following contains a code snippet illustrating how to use the model generate content based on given inputs. +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "qihoo360/Light-IF-14B" + +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto" +) + +prompt = "帮我写一份国庆节旅游攻略，要求有8个主题，每个主题的小标题用【】显示。每个主题不少于2句，不超过5句（不包含主题）。整个攻略一共是20行（以单个换行符分割，20行不包括主题）。整个攻略不超过300字。" +messages = [ + {"role": "user", "content": prompt} +] +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, + enable_thinking=True +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +generated_ids = model.generate( + **model_inputs, + max_new_tokens=32768 +) +output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() + +# parsing thinking content +try: + # rindex finding 151668 () + index = len(output_ids) - output_ids[::-1].index(151668) +except ValueError: + index = 0 + +thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n") +content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n") + +print("thinking content:", thinking_content) +print("content:", content) +``` + +**thinking content:** +
+好的，我现在需要帮用户写一份国庆节旅游攻略，满足几个具体要求。首先，需要8个主题，每个主题的小标题用【】显示。然后每个主题的内容要有2到5句（不包含主题）。整个攻略一共20行，用单个换行符分隔，20行不包括主题。还要不超过300字。 + +首先，我需要确定国庆节常见的旅游主题，比如景点推荐、美食、交通、住宿、注意事项等等。然后每个主题下要有2-5句内容。接下来，计算总行数。8个主题，每个主题可能包含多少行？需要总行数20行，所以每个主题大约2-3行？ + +但每个主题的小标题是单独一行吗？比如【主题一】作为一行，然后主题内容行数。所以总行数包括主题行吗？用户说“20行（以单个换行符分割，20行不包括主题）”。可能是指不包括主题的小标题行？需要确认。可能用户的意思是整个攻略中，除了主题小标题之外的内容行是20行？或者整个攻略总行数是20行，其中主题小标题算行吗？可能需要仔细分析。 + +比如，用户说“整个攻略一共是20行（以单个换行符分割，20行不包括主题）”，所以主题的小标题不计入这20行。那需要主题下的内容行数总和是20行？ + +然后每个主题需要2-5句，也就是每个主题的内容行数是2-5行？需要8个主题，所以总行数是8个主题各自的内容行数之和等于20行。需要分配每个主题的内容行数。比如，有些主题用3行，有些用2行？ + +比如，假设大部分主题用2行，可能需要8个主题×2行=16行，不够20行，所以需要部分主题用3行。比如4个主题用3行，4个用2行？这样总行数4×3+4×2=12+8=20行。这样分配可能更合理。 + +接下来，确定主题： + +可能的主题： + +1. 【热门景点】 +2. 【特色美食】 +3. 【交通推荐】 +4. 【住宿建议】 +5. 【亲子活动】 +6. 【摄影打卡】 +7. 【购物优惠】 +8. 【安全提示】 + +然后每个主题的内容需要2-5句，不超过300字。现在需要构造每个主题的内容行。 + +例如： + +主题1：热门景点。可能的内容行： +- 长城、故宫等经典景点人流量大，建议提前预约。 +- 选择早班或错峰出行更省时。 + +这样是2行。 + +主题2：特色美食。可能： +- 北京烤鸭、老北京炸酱面是必尝美食。 +- 居庸关长城脚下的农家菜也别有风味。 +这样2行？ + +但可能需要调整行数。比如主题2用3行？ + +需要总行数20行，8个主题，每个主题的内容行数加起来20行。比如： + +假设： + +主题1：3行（这样总行数开始是3） + +主题2：3行 → 6 + +主题3：3 →9 + +主题4：3→12 + +主题5：3→15 + +主题6：2→17 + +主题7：2→19 + +主题8：1→20？不行，每个主题需要至少2句，即至少2行？用户说每个主题不少于2句，不超过5句（不包含主题）。所以每个主题的内容行数至少2行，最多5行。所以主题8必须至少2行，所以前面可能调整： + +比如主题1-6各3行，主题7-8各2行？这样总行数：6×3 +2×2=18+4=22，超过了20，需要调整。 + +比如主题1-5各3行，主题6-8各（20-5×3）=5行？不，这样可能复杂。另一种分配： + +需要总行数20行，8个主题，每个主题2-5行。可能的组合： + +比如： + +主题行数分布：3,3,3,3,2,2,2,3 →总和是3×5+2×3+3=15+6+3=24？不对，可能需要重新计算。 + +另一种方式，每个主题的行数： + +假设5个主题用3行，3个主题用2行。总行数5×3+3×2=15+6=21，接近20，差1行。所以可能调整其中一个主题用2行，其他4个用3行，3个用2行？ + +比如：4个主题用3行，4个主题用2行？总行数4×3+4×2=12+8=20行。完美。 + +这样安排：4个主题3行，4个主题2行。 + +现在需要确定主题内容： + +比如： + +主题1：热门景点（3行） + +行1：长城、故宫等经典景点人流量大，建议提前预约。 + +行2：选择早班或错峰出行更省时。 + +行3：周边小众景点如慕田峪长城人少景美。 + +这样3行。 + +主题2：特色美食（3行） + +行1：北京烤鸭、老北京炸酱面是必尝美食。 + +行2：护城河边的胡同小吃摊位提供地道滋味。 + +行3：注意部分餐厅需提前订位。 + +3行？ + +主题3：交通推荐（3行） + +行1：地铁是出行首选，国庆期间加密班次。 + +行2：机场快线直达核心景区，节省时间。 + +行3：共享单车覆盖主要景点，适合短途。 + +3行。 + +主题4：住宿建议（3行） + +行1：市中心酒店价格较高，建议提前两周预订。 + +行2：郊区民宿性价比高，还能体验当地文化。 + +行3：注意查看住宿的防疫要求。 + +3行。 + +然后剩下的4个主题用2行： + +主题5：亲子活动（2行） + +行1：儿童乐园、科技馆有专门国庆活动。 + +行2：家长可参与亲子手工课程，增进互动。 + +主题6：摄影打卡（2行） + +行1：天安门广场、国家大剧院是热门取景点。 + +行2：黄昏时分光线柔和，更容易拍出大片。 + +主题7：购物优惠（2行） + +行1：大型商圈有满减活动，适合囤货。 + +行2：景区周边小店可淘特色纪念品。 + +主题8：安全提示（2行） + +行1：注意保管随身物品，避免人流拥挤时丢失。 + +行2：备好常用药品，应对突发小状况。 + +现在检查总行数： + +主题1：3行 + +主题2：3行 →6 + +主题3：3→9 + +主题4：3→12 + +主题5：2→14 + +主题6：2→16 + +主题7：2→18 + +主题8：2→20行。刚好20行，符合要求。 + +接下来检查每个主题的句子数是否符合2-5句（不包含主题）。每个主题的内容行数即句子数吗？可能需要调整句子是否完整，每个行是一句话吗？是的，用户可能认为每行是句子。所以每个主题的内容行数等于句子数吗？ + +比如主题1的3行是3个句子？这样主题1有3句，符合2-5句。 + +现在需要确保总字数不超过300字。 + +现在开始写具体内容，计算字数： + +主题1： + +1. 长城、故宫等经典景点人流量大，建议提前预约。（约25字） + +2. 选择早班或错峰出行更省时。（约16字） + +3. 周边小众景点如慕田峪长城人少景美。（约20字）→总约25+16+20=61字 + +主题2： + +1. 北京烤鸭、老北京炸酱面是必尝美食。（约18字） + +2. 护城河边的胡同小吃摊位提供地道滋味。（约19字） + +3. 注意部分餐厅需提前订位。（约12字）→总约18+19+12=49字 + +主题3： + +1. 地铁是出行首选，国庆期间加密班次。（约17字） + +2. 机场快线直达核心景区，节省时间。（约16字） + +3. 共享单车覆盖主要景点，适合短途。（约16字）→总17+16+16=49字 + +主题4： + +1. 市中心酒店价格较高，建议提前两周预订。（约20字） + +2. 郊区民宿性价比高，还能体验当地文化。（约21字） + +3. 注意查看住宿的防疫要求。（约13字）→总20+21+13=54字 + +主题5： + +1. 儿童乐园、科技馆有专门国庆活动。（约17字） + +2. 家长可参与亲子手工课程，增进互动。（约16字）→33字 + +主题6： + +1. 天安门广场、国家大剧院是热门取景点。（约17字） + +2. 黄昏时分光线柔和，更容易拍出大片。（约16字）→33字 + +主题7： + +1. 大型商圈有满减活动，适合囤货。（约15字） + +2. 景区周边小店可淘特色纪念品。（约14字）→29字 + +主题8： + +1. 注意保管随身物品，避免人流拥挤时丢失。（约20字） + +2. 备好常用药品，应对突发小状况。（约14字）→34字 + +现在总字数：61+49+49+54+33+33+29+34=392字？超过了300字，不符合要求。 + +需要调整，减少字数。可能需要缩短句子。 + +比如主题1的第3句：“周边小众景点如慕田峪人少景美。” 这样减少“长城”两字？或者调整句子结构。 + +需要总字数不超过300，所以需要缩短每个主题的内容。 + +可能调整如下： + +主题1： + +1. 长城、故宫人流量大，建议提前预约。 + +2. 早班或错峰出行更省时。 + +3. 慕田峪等小景点人少景美。 + +这样3行，字数约：18+13+13=44字？ + +主题2： + +1. 北京烤鸭是必尝美食。 + +2. 胡同小吃摊位有地道滋味。 + +3. 部分餐厅需提前订位。 + +3行，约：9+11+8=28字？ + +主题3： + +1. 地铁是出行首选，国庆加密班次。 + +2. 机场快线直达景区，节省时间。 + +3. 共享单车覆盖景点，方便短途。 + +3行，约：16+15+12=43字？ + +主题4： + +1. 市中心酒店价格高，建议提前预订。 + +2. 郊区民宿性价比高，体验当地文化。 + +3. 注意查看防疫要求。 + +3行，约：16+18+8=42字？ + +主题5： + +1. 儿童乐园、科技馆有国庆活动。 + +2. 家长可参与亲子课程，增进互动。 + +2行，约：14+13=27字？ + +主题6： + +1. 天安门广场、国家大剧院是热门景点。 + +2. 黄昏光线柔和，适合拍照。 + +2行，约：17+10=27字？ + +主题7： + +1. 大型商圈有满减，适合购物。 + +2. 景区小店可淘纪念品。 + +2行，约：10+11=21字？ + +主题8： + +1. 注意保管物品，避免丢失。 + +2. 备好常用药品应对突发状况。 + +2行，约：12+12=24字？ + +现在总字数： + +主题1:44 + +主题2:28 + +主题3:43 + +主题4:42 + +主题5:27 + +主题6:27 + +主题7:21 + +主题8:24 →44+28=72, +43=115, +42=157, +27=184, +27=211, +21=232, +24=256字，符合300以内。 + +现在需要调整句子更简短，确保每个主题内容符合要求。 + +现在具体写： + +【热门景点】 + +长城、故宫人流量大，建议提前预约。 + +早班或错峰出行更省时。 + +慕田峪等小景点人少景美。 + +（3行） + +【特色美食】 + +北京烤鸭是必尝美食。 + +胡同小吃摊位有地道滋味。 + +部分餐厅需提前订位。 + +（3行） + +【交通推荐】 + +地铁是出行首选，国庆加密班次。 + +机场快线直达景区，节省时间。 + +共享单车覆盖景点，方便短途。 + +（3行） + +【住宿建议】 + +市中心酒店价格高，建议提前预订。 + +郊区民宿性价比高，体验当地文化。 + +注意查看防疫要求。 + +（3行） + +【亲子活动】 + +儿童乐园、科技馆有国庆活动。 + +家长可参与亲子课程，增进互动。 + +（2行）→这里之前是2行？但需要主题行数是2行吗？前面分配是主题5用2行，是的。 + +【摄影打卡】 + +天安门广场、国家大剧院是热门景点。 + +黄昏光线柔和，适合拍照。 + +（2行） + +【购物优惠】 + +大型商圈有满减，适合购物。 + +景区小店可淘纪念品。 + +（2行） + +【安全提示】 + +注意保管物品，避免丢失。 + +备好常用药品应对突发状况。 + +（2行） + +现在检查总行数： + +主题小标题行不算，内容行数： + +主题1：3行 →行1-3 + +主题2：3 →4-6 + +主题3：3→7-9 + +主题4：3→10-12 + +主题5：2→13-14 + +主题6：2→15-16 + +主题7：2→17-18 + +主题8：2→19-20 + +刚好20行？是的。现在检查每个主题的句子数是否符合2-5句。每个主题的内容行数是： + +主题1：3句（符合） + +主题2：3句（符合） + +主题3：3句（符合） + +主题4：3句（符合） + +主题5：2句（符合） + +主题6：2句（符合） + +主题7：2句（符合） + +主题8：2句（符合） + +这样满足每个主题不少于2句，不超过5句。 + +现在检查总字数是否不超过300字。之前估算大约256字，符合要求。 + +可能需要调整部分句子，比如“国庆加密班次”是否通顺？“地铁是出行首选，国庆加密班次。” 这样没问题。 + +现在再检查： + +主题1： + +1. 长城、故宫人流量大，建议提前预约。（25字？可能更短） + +可能需要更简短的句子： + +比如“长城、故宫人流量大，需预约。” 这样更简短？ + +调整后： + +主题1： + +长城、故宫人流量大，需预约。 + +早班或错峰出行更省时。 + +慕田峪等小景点人少景美。 + +这样字数更少，总字数会减少。 + +可能这样调整： + +主题1： + +1. 长城、故宫人流量大，需预约。（16字） + +2. 早班或错峰出行更省时。（13字） + +3. 慕田峪等小景点人少景美。（15字）→总44字？ + +可能这样更合适。 + +现在最终调整： + +【热门景点】 + +长城、故宫人流量大，需预约。 + +早班或错峰出行更省时。 + +慕田峪等小景点人少景美。 + +【特色美食】 + +北京烤鸭是必尝美食。 + +胡同小吃摊位有地道滋味。 + +部分餐厅需提前订位。 + +【交通推荐】 + +地铁是出行首选，国庆加密班次。 + +机场快线直达景区，节省时间。 + +共享单车覆盖景点，方便短途。 + +【住宿建议】 + +市中心酒店价格高，建议提前预订。 + +郊区民宿性价比高，体验当地文化。 + +注意查看防疫要求。 + +【亲子活动】 + +儿童乐园、科技馆有国庆活动。 + +家长可参与亲子课程，增进互动。 + +【摄影打卡】 + +天安门广场、国家大剧院是热门景点。 + +黄昏光线柔和，适合拍照。 + +【购物优惠】 + +大型商圈有满减，适合购物。 + +景区小店可淘纪念品。 + +【安全提示】 + +注意保管物品，避免丢失。 + +备好常用药品应对突发状况。 + +现在检查行数是否20行： + +每个主题的内容行： + +主题1：3行 + +主题2：3行 →累计6 + +主题3：3→9 + +主题4：3→12 + +主题5：2→14 + +主题6：2→16 + +主题7：2→18 + +主题8：2→20 + +是的，刚好20行。 + +现在检查字数： + +大致估算： + +主题1: 16+13+15=44 + +主题2: 9+11+8=28（北京烤鸭是必尝美食→9字？可能需要重新计算字数。） + +可能我之前估算方式不太准确，但总字数应该在300以内。例如： + +每个行的大致字数： + +主题1: + +1. 长城、故宫人流量大，需预约。→17字（长城、2，故宫2，人流量大4，需预约3→17？） + +可能更准确的方式是数每个句子的字数： + +例如： + +1. 长城、故宫人流量大，需预约。→17字 + +2. 早班或错峰出行更省时。→13字 + +3. 慕田峪等小景点人少景美。→14字（慕田峪等小景点人少景美：慕田峪3，等1，小景点3，人少2，景美2→3+1+3+2+2=11？可能我数的方式有问题，但大概总字数不会超过300。） + +不管怎样，现在需要确保总字数不超过300。可能现在这样写是符合要求的。 + +现在确认： + +所有内容行： + +行1：长城、故宫人流量大，需预约。 + +行2：早班或错峰出行更省时。 + +行3：慕田峪等小景点人少景美。 + +行4：北京烤鸭是必尝美食。 + +行5：胡同小吃摊位有地道滋味。 + +行6：部分餐厅需提前订位。 + +行7：地铁是出行首选，国庆加密班次。 + +行8：机场快线直达景区，节省时间。 + +行9：共享单车覆盖景点，方便短途。 + +行10：市中心酒店价格高，建议提前预订。 + +行11：郊区民宿性价比高，体验当地文化。 + +行12：注意查看防疫要求。 + +行13：儿童乐园、科技馆有国庆活动。 + +行14：家长可参与亲子课程，增进互动。 + +行15：天安门广场、国家大剧院是热门景点。 + +行16：黄昏光线柔和，适合拍照。 + +行17：大型商圈有满减，适合购物。 + +行18：景区小店可淘纪念品。 + +行19：注意保管物品，避免丢失。 + +行20：备好常用药品应对突发状况。 + +现在数一下总字数： + +行1：17 + +行2：13 →30 + +行3：14→44 + +行4：9→53（北京烤鸭是必尝美食→9字？“北京烤鸭是必尝美食”共9字？可能需要重新数： + +“北京烤鸭是必尝美食”→北京（2）烤鸭（2）是（1）必尝（2）美食（2）→2+2+1+2+2=9？ + +行5：“胡同小吃摊位有地道滋味。”→胡同（2）小吃（2）摊位（2）有（1）地道（2）滋味（2）→2+2+2+1+2+2？不，句子是“胡同小吃摊位有地道滋味。” 共11字？ + +可能我之前的方法不太对，但无论如何，总字数大概在20行×平均15字=300字左右？需要更准确计算吗？ + +可能现在不需要精确到每个字，只要不超过300即可。根据之前的调整，应该没问题。 + +现在确认每个主题的小标题用【】显示，所以最终的攻略结构是： + +【热门景点】 + +长城、故宫人流量大，需预约。 + +早班或错峰出行更省时。 + +慕田峪等小景点人少景美。 + +【特色美食】 + +北京烤鸭是必尝美食。 + +胡同小吃摊位有地道滋味。 + +部分餐厅需提前订位。 + +【交通推荐】 + +地铁是出行首选，国庆加密班次。 + +机场快线直达景区，节省时间。 + +共享单车覆盖景点，方便短途。 + +【住宿建议】 + +市中心酒店价格高，建议提前预订。 + +郊区民宿性价比高，体验当地文化。 + +注意查看防疫要求。 + +【亲子活动】 + +儿童乐园、科技馆有国庆活动。 + +家长可参与亲子课程，增进互动。 + +【摄影打卡】 + +天安门广场、国家大剧院是热门景点。 + +黄昏光线柔和，适合拍照。 + +【购物优惠】 + +大型商圈有满减，适合购物。 + +景区小店可淘纪念品。 + +【安全提示】 + +注意保管物品，避免丢失。 + +备好常用药品应对突发状况。 + +现在检查是否符合所有要求： + +- 8个主题，小标题用【】显示：是。 + +- 每个主题不少于2句，不超过5句：每个主题的内容行数是3或2，符合。 + +- 整个攻略一共20行（不包括主题）：是的，20行。 + +- 不超过300字：大概估算： + +行1-3：主题1的3行，约17+13+14=44字 + +行4-6：主题2的3行，约9+11+10=30字（假设部分餐厅需提前订位→10字） + +行7-9：主题3的3行，约16+12+12=40字（地铁是出行首选，国庆加密班次→16字？可能需要更准确：地铁是出行首选，国庆加密班次→14字？） + +不管怎样，总字数大概在44+30+40+40+30+30+20+20=244字？应该远低于300，符合要求。 + +现在可能需要调整部分句子，使更流畅。 + +比如主题4的“注意查看防疫要求。” 是一句，没问题。 + +主题7的“大型商圈有满减，适合购物。” 是一句。 + +现在确认所有内容符合要求，没有问题。 + +这样应该满足用户的所有要求了。 +
+ +**content:** +
+【热门景点】 + +长城、故宫人流量大，需预约。 + +早班或错峰出行更省时。 + +慕田峪等小景点人少景美。 + +【特色美食】 + +北京烤鸭是必尝美食。 + +胡同小吃摊位有地道滋味。 + +部分餐厅需提前订位。 + +【交通推荐】 + +地铁是出行首选，国庆加密班次。 + +机场快线直达景区，节省时间。 + +共享单车覆盖景点，方便短途。 + +【住宿建议】 + +市中心酒店价格高，建议提前预订。 + +郊区民宿性价比高，体验当地文化。 + +注意查看防疫要求。 + +【亲子活动】 + +儿童乐园、科技馆有国庆活动。 + +家长可参与亲子课程，增进互动。 + +【摄影打卡】 + +天安门广场、国家大剧院是热门景点。 + +黄昏光线柔和，适合拍照。 + +【购物优惠】 + +大型商圈有满减，适合购物。 + +景区小店可淘纪念品。 + +【安全提示】 + +注意保管物品，避免丢失。 + +备好常用药品应对突发状况。 +
+ +For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint. + +## Citation +``` +@misc{lightifproj, + title={Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following}, + author={Chenyang Wang, Liang Wen, Shousheng Jia, Xiangzheng Zhang, Liang Xu}, + year={2025}, + eprint={2508.03178}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2508.03178}, +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..804c9d7 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 17408, + "max_position_embeddings": 131072, + "max_window_layers": 40, + "model_type": "qwen3", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} 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..e4f1d31 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.51.3" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors new file mode 100644 index 0000000..7751a58 --- /dev/null +++ b/model-00001-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0702bd6694ce0c50d6d24231ef7bcf4dfb5c5387791439c4e0271639396f82ce +size 4980965792 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors new file mode 100644 index 0000000..3ba2b8b --- /dev/null +++ b/model-00002-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b2a38b07e0a2497ef3cc07da87dec9c33ecf70feb4203f6a79841a4da7bb32 +size 4991358248 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors new file mode 100644 index 0000000..415ce37 --- /dev/null +++ b/model-00003-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e13947f1ea8b755b33023a1c5b4f7a34f11aea3b3c3c1516605d0c81d2758c0f +size 4974294936 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors new file mode 100644 index 0000000..e37145c --- /dev/null +++ b/model-00004-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82082197672181277a9170dc1ea17d597dba354d36551c8d342c789ff1556ae5 +size 4974210040 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors new file mode 100644 index 0000000..0f481df --- /dev/null +++ b/model-00005-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197fa7d2884b6755f0857cb86391fb346c040ef84f934f91ccf8589b8e90cb2d +size 4928621768 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors new file mode 100644 index 0000000..d2ae74c --- /dev/null +++ b/model-00006-of-00006.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28cdce6809879f8d1e4326d607e304efe1a07424c8aa3a4492d05d01a447892 +size 4687214864 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..00cee04 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,450 @@ +{ + "metadata": { + "total_size": 29536614400 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00006.safetensors", + "model.embed_tokens.weight": "model-00003-of-00006.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.11.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.12.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.14.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.17.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00006.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00006.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.33.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.34.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.input_layernorm.weight": "model-00004-of-00006.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00006.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00006-of-00006.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00006.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00006.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00005-of-00006.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00006.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", + "model.norm.weight": "model-00006-of-00006.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6f06e44 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,241 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in message.content %}\n {%- set content = message.content.split('')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833