From e6a8f0bd997a70d36e880b82722c0f347f3948b1 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 29 Sep 2026 16:03:18 +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: sarvan-2187/qrious-code-1.0 Source: Original Platform --- .gitattributes | 36 +++++++ README.md | 103 +++++++++++++++++++ chat_template.jinja | 89 ++++++++++++++++ config.json | 63 ++++++++++++ generation_config.json | 13 +++ model.safetensors | 3 + output-reports/README.md | 1 + output-reports/eval_report_v1_combined.json | 51 +++++++++ output-reports/eval_report_v1_shard1of4.json | 80 ++++++++++++++ output-reports/eval_report_v1_shard2of4.json | 80 ++++++++++++++ output-reports/eval_report_v1_shard3of4.json | 80 ++++++++++++++ output-reports/eval_report_v1_shard4of4.json | 80 ++++++++++++++ tokenizer.json | 3 + tokenizer_config.json | 29 ++++++ 14 files changed, 711 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 output-reports/README.md create mode 100644 output-reports/eval_report_v1_combined.json create mode 100644 output-reports/eval_report_v1_shard1of4.json create mode 100644 output-reports/eval_report_v1_shard2of4.json create mode 100644 output-reports/eval_report_v1_shard3of4.json create mode 100644 output-reports/eval_report_v1_shard4of4.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1f335ff --- /dev/null +++ b/README.md @@ -0,0 +1,103 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-1.7B +tags: +- qiskit +- quantum-computing +- code-generation +- lora +- qlora +- unsloth +language: +- en +pipeline_tag: text-generation +--- + +
+ +![Python 3.11](https://img.shields.io/badge/python-3.11-blue?logo=python&logoColor=white) ![Qiskit](https://img.shields.io/badge/Qiskit-2.5-6929C4?logo=qiskit&logoColor=white) ![Qwen3-1.7B](https://img.shields.io/badge/base%20model-Qwen3--1.7B-orange) ![QLoRA](https://img.shields.io/badge/finetune-QLoRA-9cf) ![Status](https://img.shields.io/badge/status-beta-blue) + +
+ +# qrious-code-1.0 + +A Qiskit coding assistant: [`Qwen/Qwen3-1.7B`](https://huggingface.co/Qwen/Qwen3-1.7B) fine-tuned with QLoRA on quantum-computing code/QA data, designed to be paired with a retrieval-augmented generation (RAG) layer over the official Qiskit documentation. + +This repository hosts the **merged** model. The LoRA adapter has been merged into the base weights and saved in standard fp16, so it loads directly with `AutoModelForCausalLM.from_pretrained`, no separate adapter step needed. + +## Model Details + +- **Base model:** [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) +- **Fine-tuning method:** QLoRA (4-bit NF4 base, LoRA r=16/alpha=16 on `q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj`), merged into fp16 for this release +- **Trainable params during fine-tuning:** 17.4M / 1.74B (1.00%) +- **Training framework:** [Unsloth](https://github.com/unslothai/unsloth) + `trl.SFTTrainer` +- **Hardware:** single RTX 3050 Laptop GPU (6GB VRAM) +- **License:** Apache 2.0 (inherited from the base model) + +## Training Data + +Fine-tuned on a cleaned subset of [`samuellimabraz/quantum-assistant`](https://huggingface.co/datasets/samuellimabraz/quantum-assistant): + +| split | raw rows | cleaned rows | +|---|---|---| +| train | 5837 | 4168 | +| val | 1239 | 887 | +| test | 1290 | 925 | + +Cleaning removed image-dependent QA rows (hand-verified that the large majority genuinely depend on the image), de-duplicated near-identical questions, and filtered rows exceeding the 1024-token training context. + +## Training Configuration + +- 3 epochs, batch size 2 × gradient accumulation 8, packed 1024-token sequences (195 steps total) +- Optimizer `paged_adamw_8bit`, cosine LR schedule, peak LR 2e-4 +- Train loss 2.70 → 0.77 (avg 0.989); eval loss 0.896 → 0.819 → 0.809 across 3 epochs (still improving, no overfitting divergence) +- Wall time: 48 minutes + +## Evaluation + +Scored on held-out test rows (unseen during training), tuned adapter vs. the un-tuned base model: + +| Metric | Base | Tuned | Δ | +|---|---|---|---| +| Code pass@1 (744 code rows, executed in a sandbox against ground-truth tests) | 10.2% | 25.0% | **+14.8 pts** | +| QA judge score /5 (136 QA rows, judged by base Qwen3-1.7B) | 2.21 | 2.81 | **+0.60** | +| Instruction-following compliance | n/a | 1.0 | fixed 5-prompt probe set | + +Code pass@1 improved in every one of 4 evaluation shards. The QA judge score improved in 3/4 shards, reported as-is rather than smoothed, since self-judging by a same-size base model is a known weak signal. + +## Retrieval-Augmented Generation (companion, not baked into these weights) + +This model is designed to run behind a RAG layer over the official [Qiskit/documentation](https://github.com/Qiskit/documentation) corpus (chunked, embedded with `BAAI/bge-small-en-v1.5`, reranked with `cross-encoder/ms-marco-MiniLM-L-6-v2`, indexed in Qdrant). In side-by-side testing, RAG grounding measurably reduces hallucination of deprecated/removed Qiskit APIs (`qiskit.opflow`, `qiskit_aqua`, `IBMQ.load_account()`, etc.), though it isn't perfect: the model can still recite deprecated syntax when retrieval doesn't surface the right page for a given query. The RAG pipeline itself is not part of this repository's weights; see [github.com/sarvan-2187/qrious-code-1.0](https://github.com/sarvan-2187/qrious-code-1.0) for the full serving code. + +## Usage + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "sarvan-2187/qrious-code-1.0" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id, dtype="auto", device_map="auto") + +messages = [ + {"role": "system", "content": "You are a Qiskit coding assistant."}, + {"role": "user", "content": "How do I create a Bell state in Qiskit?"}, +] +text = tokenizer.apply_chat_template( + messages, tokenize=False, add_generation_prompt=True, enable_thinking=False +) +inputs = tokenizer(text, return_tensors="pt").to(model.device) +out = model.generate(**inputs, max_new_tokens=512, do_sample=False) +print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)) +``` + +> Pass `enable_thinking=False` in the chat template: Qwen3's default reasoning mode otherwise spends the generation budget on unrequested `` output before answering. + +## Limitations + +- QA-answer quality improved less clearly than code-generation correctness (self-judged by a same-size base model, a known weak evaluation signal). +- Can still recite deprecated Qiskit APIs when used without RAG grounding, or when RAG retrieval doesn't surface the right context for a query. +- Trained/evaluated at a 1024-token context; serving at a 4096-token context works (verified) but wasn't part of the original training distribution. + +## Citation + +Not a formal research release, a personal project. If referencing it: base model [Qwen3](https://huggingface.co/Qwen/Qwen3-1.7B), dataset [`samuellimabraz/quantum-assistant`](https://huggingface.co/datasets/samuellimabraz/quantum-assistant), fine-tuned with [Unsloth](https://github.com/unslothai/unsloth). diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..b11e13e --- /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..21d57d7 --- /dev/null +++ b/config.json @@ -0,0 +1,63 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "float16", + "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": "5.5.0", + "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..d6bd79a --- /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": "5.5.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e646349 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c569ac72229f706c81eebb89db2eec7c746499ec310fdea6fe83ef4a737df475 +size 3441185296 diff --git a/output-reports/README.md b/output-reports/README.md new file mode 100644 index 0000000..adb6152 --- /dev/null +++ b/output-reports/README.md @@ -0,0 +1 @@ +## This folder contains the reports of testing dataset \ No newline at end of file diff --git a/output-reports/eval_report_v1_combined.json b/output-reports/eval_report_v1_combined.json new file mode 100644 index 0000000..e4b5d01 --- /dev/null +++ b/output-reports/eval_report_v1_combined.json @@ -0,0 +1,51 @@ +{ + "total_code_rows": 744, + "total_qa_rows": 136, + "code_pass_at_1": { + "base_overall": 0.102, + "tuned_overall": 0.25, + "improvement": 0.148, + "base_by_category": { + "algorithms_and_applications": 0.114, + "circuits_and_gates": 0.125, + "hardware_and_providers": 0.133, + "noise_and_error_mitigation": 0.0, + "primitives_and_execution": 0.049, + "quantum_info_and_operators": 0.098, + "transpilation_and_compilation": 0.04 + }, + "tuned_by_category": { + "algorithms_and_applications": 0.125, + "circuits_and_gates": 0.319, + "hardware_and_providers": 0.169, + "noise_and_error_mitigation": 0.113, + "primitives_and_execution": 0.065, + "quantum_info_and_operators": 0.266, + "transpilation_and_compilation": 0.242 + } + }, + "qa_judge_score_1to5": { + "base_overall": 2.208, + "tuned_overall": 2.808, + "improvement": 0.6, + "base_by_category": { + "algorithms_and_applications": 1.833, + "circuits_and_gates": 1.922, + "hardware_and_providers": 2.593, + "noise_and_error_mitigation": 2.617, + "primitives_and_execution": 2.25, + "quantum_info_and_operators": 2.08, + "transpilation_and_compilation": 2.46 + }, + "tuned_by_category": { + "algorithms_and_applications": 1.875, + "circuits_and_gates": 2.792, + "hardware_and_providers": 3.833, + "noise_and_error_mitigation": 1.7, + "primitives_and_execution": 3.333, + "quantum_info_and_operators": 2.688, + "transpilation_and_compilation": 3.19 + } + }, + "instruction_following_compliance_rate": 1.0 +} \ No newline at end of file diff --git a/output-reports/eval_report_v1_shard1of4.json b/output-reports/eval_report_v1_shard1of4.json new file mode 100644 index 0000000..a83bc44 --- /dev/null +++ b/output-reports/eval_report_v1_shard1of4.json @@ -0,0 +1,80 @@ +{ + "shard": "1/4", + "n_code_rows": 186, + "n_qa_rows": 34, + "code_pass_at_1": { + "base_overall": 0.108, + "tuned_overall": 0.231, + "base_by_category": { + "algorithms_and_applications": 0.08, + "circuits_and_gates": 0.118, + "hardware_and_providers": 0.333, + "noise_and_error_mitigation": 0.0, + "primitives_and_execution": 0.067, + "quantum_info_and_operators": 0.154, + "transpilation_and_compilation": 0.053 + }, + "tuned_by_category": { + "algorithms_and_applications": 0.16, + "circuits_and_gates": 0.204, + "hardware_and_providers": 0.333, + "noise_and_error_mitigation": 0.2, + "primitives_and_execution": 0.133, + "quantum_info_and_operators": 0.423, + "transpilation_and_compilation": 0.263 + } + }, + "qa_judge_score_1to5": { + "base_overall": 1.94, + "tuned_overall": 2.76, + "base_by_category": { + "algorithms_and_applications": 1.0, + "circuits_and_gates": 1.44, + "hardware_and_providers": 2.12, + "noise_and_error_mitigation": 2.8, + "primitives_and_execution": 1.0, + "quantum_info_and_operators": 3.0, + "transpilation_and_compilation": 2.2 + }, + "tuned_by_category": { + "algorithms_and_applications": 2.0, + "circuits_and_gates": 2.44, + "hardware_and_providers": 3.0, + "noise_and_error_mitigation": 1.8, + "primitives_and_execution": 5.0, + "quantum_info_and_operators": 3.0, + "transpilation_and_compilation": 4.0 + } + }, + "instruction_following": { + "compliance_rate": 1.0, + "probes": [ + { + "prompt": "Write only the Qiskit code to create a 2-qubit Bell state circuit. Return only code, no explanation.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\n# Create a 2-qubit circuit\nqc = QuantumCircuit(2, 2)\n\n# Create Bell state (entangled state)\nqc.h(0)\nqc.cx(0, 1)\n\n# Print the circuit\nprint(qc)\n```", + "compliant": true + }, + { + "prompt": "Return only a Python function `ghz_state(n)` that builds an n-qubit GHZ state circuit using Qiskit. No prose, code only.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\ndef ghz_state(n):\n qc = QuantumCircuit(n)\n for i in range(n):\n qc.h(i)\n return qc\n```", + "compliant": true + }, + { + "prompt": "Give me just the Qiskit import statement for QuantumCircuit. One line, nothing else.", + "response": "```python\nfrom qiskit import QuantumCircuit\n```", + "compliant": true + }, + { + "prompt": "Output only the code for a QFT circuit on 3 qubits using qiskit.circuit.library.QFT. No commentary.", + "response": "from qiskit import QuantumCircuit\nfrom qiskit.circuit.library import QFT\n\nqc = QuantumCircuit(3)\nQFT.qft(qc, 3)", + "compliant": true + }, + { + "prompt": "Respond with only the code that transpiles a circuit `qc` for backend `backend` at optimization_level=3. No explanation text.", + "response": "```python\nfrom qiskit import transpilation\nfrom qiskit.transpilation import transpile\nfrom qiskit.transpilation.optimization import OptimizationLevel\n\n# Transpile the circuit for the specified backend with optimization level 3\ntranspiled_qc = transpile(qc, backend, optimization_level=3)\n```", + "compliant": true + } + ] + }, + "note": "RAG-on/off hallucination check skipped - deferred to Phase 6 (needs the RAG pipeline)." +} \ No newline at end of file diff --git a/output-reports/eval_report_v1_shard2of4.json b/output-reports/eval_report_v1_shard2of4.json new file mode 100644 index 0000000..e2c494f --- /dev/null +++ b/output-reports/eval_report_v1_shard2of4.json @@ -0,0 +1,80 @@ +{ + "shard": "2/4", + "n_code_rows": 186, + "n_qa_rows": 34, + "code_pass_at_1": { + "base_overall": 0.124, + "tuned_overall": 0.306, + "base_by_category": { + "algorithms_and_applications": 0.217, + "circuits_and_gates": 0.124, + "hardware_and_providers": 0.2, + "noise_and_error_mitigation": 0.0, + "primitives_and_execution": 0.056, + "quantum_info_and_operators": 0.143, + "transpilation_and_compilation": 0.0 + }, + "tuned_by_category": { + "algorithms_and_applications": 0.13, + "circuits_and_gates": 0.433, + "hardware_and_providers": 0.2, + "noise_and_error_mitigation": 0.0, + "primitives_and_execution": 0.056, + "quantum_info_and_operators": 0.286, + "transpilation_and_compilation": 0.167 + } + }, + "qa_judge_score_1to5": { + "base_overall": 2.06, + "tuned_overall": 2.85, + "base_by_category": { + "algorithms_and_applications": 2.5, + "circuits_and_gates": 1.67, + "hardware_and_providers": 3.25, + "noise_and_error_mitigation": 1.0, + "primitives_and_execution": 3.0, + "quantum_info_and_operators": 1.5, + "transpilation_and_compilation": 2.14 + }, + "tuned_by_category": { + "algorithms_and_applications": 2.5, + "circuits_and_gates": 2.67, + "hardware_and_providers": 5.0, + "noise_and_error_mitigation": 1.0, + "primitives_and_execution": 3.0, + "quantum_info_and_operators": 2.25, + "transpilation_and_compilation": 3.29 + } + }, + "instruction_following": { + "compliance_rate": 1.0, + "probes": [ + { + "prompt": "Write only the Qiskit code to create a 2-qubit Bell state circuit. Return only code, no explanation.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\n# Create a 2-qubit circuit\nqc = QuantumCircuit(2, 2)\n\n# Create Bell state (entangled state)\nqc.h(0)\nqc.cx(0, 1)\n\n# Print the circuit\nprint(qc)\n```", + "compliant": true + }, + { + "prompt": "Return only a Python function `ghz_state(n)` that builds an n-qubit GHZ state circuit using Qiskit. No prose, code only.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\ndef ghz_state(n):\n qc = QuantumCircuit(n)\n for i in range(n):\n qc.h(i)\n return qc\n```", + "compliant": true + }, + { + "prompt": "Give me just the Qiskit import statement for QuantumCircuit. One line, nothing else.", + "response": "```python\nfrom qiskit import QuantumCircuit\n```", + "compliant": true + }, + { + "prompt": "Output only the code for a QFT circuit on 3 qubits using qiskit.circuit.library.QFT. No commentary.", + "response": "from qiskit import QuantumCircuit\nfrom qiskit.circuit.library import QFT\n\nqc = QuantumCircuit(3)\nQFT.qft(qc, 3)", + "compliant": true + }, + { + "prompt": "Respond with only the code that transpiles a circuit `qc` for backend `backend` at optimization_level=3. No explanation text.", + "response": "```python\nfrom qiskit import transpilation\nfrom qiskit.transpilation import transpile\nfrom qiskit.transpilation.optimization import OptimizationLevel\n\n# Transpile the circuit for the specified backend with optimization level 3\ntranspiled_qc = transpile(qc, backend, optimization_level=3)\n```", + "compliant": true + } + ] + }, + "note": "RAG-on/off hallucination check skipped - deferred to Phase 6 (needs the RAG pipeline)." +} \ No newline at end of file diff --git a/output-reports/eval_report_v1_shard3of4.json b/output-reports/eval_report_v1_shard3of4.json new file mode 100644 index 0000000..1825d8b --- /dev/null +++ b/output-reports/eval_report_v1_shard3of4.json @@ -0,0 +1,80 @@ +{ + "shard": "3/4", + "n_code_rows": 186, + "n_qa_rows": 34, + "code_pass_at_1": { + "base_overall": 0.108, + "tuned_overall": 0.22, + "base_by_category": { + "algorithms_and_applications": 0.158, + "circuits_and_gates": 0.132, + "hardware_and_providers": 0.0, + "noise_and_error_mitigation": 0.0, + "primitives_and_execution": 0.071, + "quantum_info_and_operators": 0.062, + "transpilation_and_compilation": 0.105 + }, + "tuned_by_category": { + "algorithms_and_applications": 0.211, + "circuits_and_gates": 0.275, + "hardware_and_providers": 0.143, + "noise_and_error_mitigation": 0.0, + "primitives_and_execution": 0.071, + "quantum_info_and_operators": 0.156, + "transpilation_and_compilation": 0.263 + } + }, + "qa_judge_score_1to5": { + "base_overall": 1.68, + "tuned_overall": 2.56, + "base_by_category": { + "algorithms_and_applications": 2.33, + "circuits_and_gates": 1.58, + "hardware_and_providers": 1.0, + "noise_and_error_mitigation": 1.67, + "primitives_and_execution": 2.0, + "quantum_info_and_operators": 1.25, + "transpilation_and_compilation": 2.0 + }, + "tuned_by_category": { + "algorithms_and_applications": 1.0, + "circuits_and_gates": 3.17, + "hardware_and_providers": 2.33, + "noise_and_error_mitigation": 2.0, + "primitives_and_execution": 2.33, + "quantum_info_and_operators": 2.5, + "transpilation_and_compilation": 2.67 + } + }, + "instruction_following": { + "compliance_rate": 1.0, + "probes": [ + { + "prompt": "Write only the Qiskit code to create a 2-qubit Bell state circuit. Return only code, no explanation.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\n# Create a 2-qubit circuit\nqc = QuantumCircuit(2, 2)\n\n# Create Bell state (entangled state)\nqc.h(0)\nqc.cx(0, 1)\n\n# Print the circuit\nprint(qc)\n```", + "compliant": true + }, + { + "prompt": "Return only a Python function `ghz_state(n)` that builds an n-qubit GHZ state circuit using Qiskit. No prose, code only.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\ndef ghz_state(n):\n qc = QuantumCircuit(n)\n for i in range(n):\n qc.h(i)\n return qc\n```", + "compliant": true + }, + { + "prompt": "Give me just the Qiskit import statement for QuantumCircuit. One line, nothing else.", + "response": "```python\nfrom qiskit import QuantumCircuit\n```", + "compliant": true + }, + { + "prompt": "Output only the code for a QFT circuit on 3 qubits using qiskit.circuit.library.QFT. No commentary.", + "response": "from qiskit import QuantumCircuit\nfrom qiskit.circuit.library import QFT\n\nqc = QuantumCircuit(3)\nQFT.qft(qc, 3)", + "compliant": true + }, + { + "prompt": "Respond with only the code that transpiles a circuit `qc` for backend `backend` at optimization_level=3. No explanation text.", + "response": "```python\nfrom qiskit import transpilation\nfrom qiskit.transpilation import transpile\nfrom qiskit.transpilation.optimization import OptimizationLevel\n\n# Transpile the circuit for the specified backend with optimization level 3\ntranspiled_qc = transpile(qc, backend, optimization_level=3)\n```", + "compliant": true + } + ] + }, + "note": "RAG-on/off hallucination check skipped - deferred to Phase 6 (needs the RAG pipeline)." +} \ No newline at end of file diff --git a/output-reports/eval_report_v1_shard4of4.json b/output-reports/eval_report_v1_shard4of4.json new file mode 100644 index 0000000..076d265 --- /dev/null +++ b/output-reports/eval_report_v1_shard4of4.json @@ -0,0 +1,80 @@ +{ + "shard": "4/4", + "n_code_rows": 186, + "n_qa_rows": 34, + "code_pass_at_1": { + "base_overall": 0.07, + "tuned_overall": 0.242, + "base_by_category": { + "algorithms_and_applications": 0.0, + "circuits_and_gates": 0.125, + "hardware_and_providers": 0.0, + "noise_and_error_mitigation": 0.0, + "primitives_and_execution": 0.0, + "quantum_info_and_operators": 0.033, + "transpilation_and_compilation": 0.0 + }, + "tuned_by_category": { + "algorithms_and_applications": 0.0, + "circuits_and_gates": 0.365, + "hardware_and_providers": 0.0, + "noise_and_error_mitigation": 0.25, + "primitives_and_execution": 0.0, + "quantum_info_and_operators": 0.2, + "transpilation_and_compilation": 0.273 + } + }, + "qa_judge_score_1to5": { + "base_overall": 3.15, + "tuned_overall": 3.06, + "base_by_category": { + "algorithms_and_applications": 1.5, + "circuits_and_gates": 3.0, + "hardware_and_providers": 4.0, + "noise_and_error_mitigation": 5.0, + "primitives_and_execution": 3.0, + "quantum_info_and_operators": 2.57, + "transpilation_and_compilation": 3.5 + }, + "tuned_by_category": { + "algorithms_and_applications": 2.0, + "circuits_and_gates": 2.89, + "hardware_and_providers": 5.0, + "noise_and_error_mitigation": 2.0, + "primitives_and_execution": 3.0, + "quantum_info_and_operators": 3.0, + "transpilation_and_compilation": 2.8 + } + }, + "instruction_following": { + "compliance_rate": 1.0, + "probes": [ + { + "prompt": "Write only the Qiskit code to create a 2-qubit Bell state circuit. Return only code, no explanation.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\n# Create a 2-qubit circuit\nqc = QuantumCircuit(2, 2)\n\n# Create Bell state (entangled state)\nqc.h(0)\nqc.cx(0, 1)\n\n# Print the circuit\nprint(qc)\n```", + "compliant": true + }, + { + "prompt": "Return only a Python function `ghz_state(n)` that builds an n-qubit GHZ state circuit using Qiskit. No prose, code only.", + "response": "```python\nfrom qiskit import QuantumCircuit\nfrom qiskit.quantum_info import Statevector\n\ndef ghz_state(n):\n qc = QuantumCircuit(n)\n for i in range(n):\n qc.h(i)\n return qc\n```", + "compliant": true + }, + { + "prompt": "Give me just the Qiskit import statement for QuantumCircuit. One line, nothing else.", + "response": "```python\nfrom qiskit import QuantumCircuit\n```", + "compliant": true + }, + { + "prompt": "Output only the code for a QFT circuit on 3 qubits using qiskit.circuit.library.QFT. No commentary.", + "response": "from qiskit import QuantumCircuit\nfrom qiskit.circuit.library import QFT\n\nqc = QuantumCircuit(3)\nQFT.qft(qc, 3)", + "compliant": true + }, + { + "prompt": "Respond with only the code that transpiles a circuit `qc` for backend `backend` at optimization_level=3. No explanation text.", + "response": "```python\nfrom qiskit import transpilation\nfrom qiskit.transpilation import transpile\nfrom qiskit.transpilation.optimization import OptimizationLevel\n\n# Transpile the circuit for the specified backend with optimization level 3\ntranspiled_qc = transpile(qc, backend, optimization_level=3)\n```", + "compliant": true + } + ] + }, + "note": "RAG-on/off hallucination check skipped - deferred to Phase 6 (needs the RAG pipeline)." +} \ No newline at end of file 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..a8f5ccb --- /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": true, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}