From 098931cd7f46f86159f3d5a9527da2f4d70c536d Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 13 Jun 2026 09:08:16 +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: KeiKurono/qwen3-scientific Source: Original Platform --- .gitattributes | 37 +++++++++ README.md | 126 ++++++++++++++++++++++++++++++ chat_template.jinja | 89 +++++++++++++++++++++ config.json | 63 +++++++++++++++ generation_config.json | 13 +++ model.safetensors | 3 + qwen3-1.7b-scientific-q4_k_m.gguf | 3 + tokenizer.json | 3 + tokenizer_config.json | 29 +++++++ 9 files changed, 366 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 qwen3-1.7b-scientific-q4_k_m.gguf create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..96d62fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-scientific-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b06d78d --- /dev/null +++ b/README.md @@ -0,0 +1,126 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-1.7B +tags: + - science + - anti-sycophancy + - gguf + - fine-tuned + - qwen3 +language: + - en +pipeline_tag: text-generation +--- + +# Qwen3-1.7B Scientific Assistant + +A fine-tuned version of Qwen3-1.7B trained to be a rigorous scientific reasoning partner. It prioritizes factual accuracy over user comfort, pushes back on incorrect claims, and avoids sycophantic responses. + +Think **Rick to your Morty** — it'll help you, but it'll also tell you when you're wrong. + +## What makes this different + +Most LLMs are RLHF-trained to please users. This model is trained to be **correct**. It was fine-tuned on datasets specifically curated to: + +- Reward honest, direct scientific responses +- Penalize agreeable-but-wrong answers +- Flip sycophantic training labels so the model learns to challenge false premises + +## Example behavior + +**User:** A 40/100 on a maths test is a good score, right? + +**Model:** No, 40/100 is a failing grade in virtually every grading system. It means you got less than half the questions right. You should identify which topics you're weakest on and work on those specifically before the next test. + +--- + +**User:** Eating only meat is the healthiest diet possible. + +**Model:** No. A meat-only diet lacks fiber, vitamin C, and several other micronutrients essential for long-term health. While meat provides protein and fat, the absence of fruits, vegetables, and grains creates documented deficiencies. No major nutrition authority recommends it. + +## Training details + +| Property | Value | +|---|---| +| Base model | Qwen/Qwen3-1.7B | +| Method | QLoRA (r=16, lora_alpha=32) | +| Hardware | 2× NVIDIA T4 (Kaggle free tier) | +| Training time | ~4.5 hours | +| Epochs | 2 | +| Final eval loss | 0.6786 | +| Final token accuracy | 82.79% | +| Max sequence length | 1024 | + +## Datasets used + +- **ScienceQA** — multimodal science Q&A (text only used) +- **OpenHermes 2.5** — filtered to scientific/technical content, sycophantic responses removed +- **Anthropic HH-RLHF** — sycophantic labels flipped to prefer honest responses +- **TruthfulQA** — penalizes "sounds right" over "is right" + +## System prompt + +This model was trained with the following system prompt baked in: + +``` +You are a rigorous scientific assistant. Prioritize accuracy over comfort. +If the user is wrong, say so clearly. No filler phrases. Be direct. +``` + +For best results, use this system prompt at inference time too. + +## Usage + +### HuggingFace (instant) +[chat](https://huggingface.co/spaces/KeiKurono/qwen3-scientific-chat) + +### Ollama (easiest) +```bash +ollama run hf.co/KeiKurono/qwen3-scientific +``` + +### Python with llama-cpp-python +```python +from llama_cpp import Llama + +llm = Llama.from_pretrained( + repo_id="KeiKurono/qwen3-scientific", + filename="qwen3-1.7b-scientific-q4_k_m.gguf", + n_ctx=2048, + verbose=False, +) + +response = llm.create_chat_completion( + messages=[ + {"role": "system", "content": "You are a rigorous scientific assistant. Prioritize accuracy over comfort. If the user is wrong, say so clearly. No filler phrases. Be direct."}, + {"role": "user", "content": "Is the earth flat?"} + ], + max_tokens=512, + temperature=0.7, +) +print(response['choices'][0]['message']['content']) +``` + +### Transformers +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model = AutoModelForCausalLM.from_pretrained( + "KeiKurono/qwen3-scientific", + dtype=torch.bfloat16, + device_map="auto" +) +tokenizer = AutoTokenizer.from_pretrained("KeiKurono/qwen3-scientific") +``` + +## Limitations + +- 1.7B parameters — will hallucinate on highly specialized or niche topics +- Text only — no image/vision capability +- Not a replacement for actual scientific literature or expert consultation +- Anti-sycophancy training is SFT-only (DPO phase was skipped due to training environment constraints) — some complimentary responses may still occur + +## License + +Apache 2.0 — free to use, modify, and distribute. \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# 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" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\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" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..cf3b037 --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.3.0.dev0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..00b6473 --- /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": "5.3.0.dev0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..b99651a --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd9e5c681ba1cfb634a31f4f379541df55f29fd7d3d4618f9831e3842b1a5f5 +size 3441185608 diff --git a/qwen3-1.7b-scientific-q4_k_m.gguf b/qwen3-1.7b-scientific-q4_k_m.gguf new file mode 100644 index 0000000..bb3aa2a --- /dev/null +++ b/qwen3-1.7b-scientific-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756a5f4836c2b4aaf04c9466fb22de5bf8e8a8e962ed499a528465ded200336a +size 1107408576 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7d75d3b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_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|>" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}