commit ac3e5c061b553f5d0cc2072f21d2ec78e571782e Author: ModelHub XC Date: Wed Jun 10 05:30:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: HelpingAI/Dhanishtha Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.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 +*.safetensors 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 + +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/AI4free_Dhanishtha-F16.gguf b/AI4free_Dhanishtha-F16.gguf new file mode 100644 index 0000000..f22bdab --- /dev/null +++ b/AI4free_Dhanishtha-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac0dea79166a48f053490a8a567056bca266718ada8b1ba685baa14cf9dd5fee +size 3560416032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d5f8884 --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: apache-2.0 +datasets: +- Abhaykoul/Dhanishtha-R1 +- open-thoughts/OpenThoughts-114k +language: +- en +base_model: +- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B +--- +# Dhanishtha Overview + +Dhanishtha is a cutting-edge reasoning AI model developed by **HelpingAI**, designed for deep introspection and structured logical analysis. Unlike traditional models that generate immediate responses, Dhanishtha employs a unique **deep-thinking process** process—an internal deliberation phase that enhances reasoning depth before presenting refined answers. + +## Model Capabilities +Dhanishtha operates in **Dhanishtha Mode**, inspired by the **Dhanishtha Nakshatra**, known for wisdom, rhythm, and intellectual depth. The model engages in a multi-step thought process before providing responses, ensuring high accuracy and coherence. + +### Key Features: +- **Structured Internal Reasoning:** Engages in self-dialogue within `` tags, iterating through ideas and refining its thought process before responding. +- **Progressive Thought Refinement:** Evaluates multiple perspectives, making logical connections and ensuring a well-rounded answer. +- **Emotionally Intelligent Conversational Style:** Responses are expressive, engaging, and tailored for natural human interaction. +- **Optimized for Critical Thinking & Problem-Solving:** Excels in analytical reasoning, debate, and deep philosophical discussions. +- **Context Awareness:** Maintains logical coherence in extended interactions, avoiding contradictions and ensuring smooth thought progression. + +## Training & Architecture +- **Model Size:** Optimized for high-performance reasoning with balanced efficiency. +- **Training Approach:** Fine-tuned using advanced structured learning techniques to enhance deliberative thinking and introspective processing. +- **Data Sources:** Trained on a diverse dataset covering philosophy, critical reasoning, and problem-solving scenarios to develop a deep intellectual foundation. + +## Performance & Benchmarks +Dhanishtha outperforms conventional models in structured reasoning and contextual depth. The model has been rigorously evaluated across various metrics, demonstrating significant improvements in: +- **Logical Coherence & Argumentation:** Enhanced ability to follow complex discussions and construct persuasive arguments. +- **Depth of Analysis:** Excels in breaking down intricate topics into clear, structured responses. +- **Adaptive Conversational Flow:** Seamlessly shifts between casual and analytical tones based on user input. + +## Deployment & Use Cases +Dhanishtha is designed for: +- **High-precision academic and philosophical discussions** +- **Deep problem-solving and strategic reasoning** +- **Engaging and thought-provoking conversations** +- **Use in AI-driven research and advanced dialogue systems** + +## Benchmarks +We report Pass@1 accuracy averaged over 16 samples for each problem. + +| Model | AIME 2024 | MATH 500 | AMC 2023 | Minerva Math | OlympiadBench | Avg. | +|-------------------------------|-----------|----------|----------|--------------|----------------|------| +| 2.5-7B-Instruct | 13.3 | 79.8 | 50.6 | 34.6 | 40.7 | 43.8 | +| rStar-Math-7B | 26.7 | 78.4 | 47.5 | - | 47.1 | - | +| Eurus-2.7B-PRIME | 26.7 | 79.2 | 57.8 | 38.6 | 42.1 | 48.9 | +| Qwen2.5-7B-SimpleRL | 26.7 | 82.4 | 62.5 | 39.7 | 43.3 | 50.9 | +| DeepSeek-R1-Distill-Qwen-1.5B | 28.8 | 82.8 | 62.9 | 26.5 | 43.3 | 48.9 | +| Still-1.5B | 32.5 | 84.4 | 66.7 | 29.0 | 45.4 | 51.6 | +| DeepScaleR-1.5B-Preview | 43.1 | 87.8 | 73.6 | 30.2 | 50.0 | 57.0 | +| O1-Preview | 40.0 | 81.4 | - | - | - | - | +| **Dhanishta** | 38.2 | 85.1 | 70.3 | 30.5 | 42.0 | 53.2 | + + +## Credits & License +Dhanishtha is developed and maintained by **HelpingAI**, pushing the boundaries of AI-driven introspection and structured reasoning. The model is open-source and community-driven, encouraging contributions and collaborative innovation. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..7e89cbf --- /dev/null +++ b/config.json @@ -0,0 +1,31 @@ +{ + "_name_or_path": "AI4free/test23", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151646, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "max_position_embeddings": 131072, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.48.3", + "use_cache": true, + "use_mrope": 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..e3ae19e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "eos_token_id": 151643, + "pad_token_id": 151643, + "transformers_version": "4.48.3" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..6b29d9b --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89a45c36d040e7c36d05310b5fe0ca32c994a5b62ca7e576d26a22dba7e9ebf +size 3554214416 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b068ffc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "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 + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}