初始化项目，由ModelHub XC社区提供模型
Model: sarvan-2187/qrious-code-1.0 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -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
|
||||
103
README.md
Normal file
103
README.md
Normal file
@@ -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
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
    
|
||||
|
||||
</div>
|
||||
|
||||
# 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 `<think>` 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).
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -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 <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|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('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- 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 '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-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<think>\n' + reasoning_content.strip('\n') + '\n</think>\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 %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- 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 %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
63
config.json
Normal file
63
config.json
Normal file
@@ -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
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -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"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c569ac72229f706c81eebb89db2eec7c746499ec310fdea6fe83ef4a737df475
|
||||
size 3441185296
|
||||
1
output-reports/README.md
Normal file
1
output-reports/README.md
Normal file
@@ -0,0 +1 @@
|
||||
## This folder contains the reports of testing dataset
|
||||
51
output-reports/eval_report_v1_combined.json
Normal file
51
output-reports/eval_report_v1_combined.json
Normal file
@@ -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
|
||||
}
|
||||
80
output-reports/eval_report_v1_shard1of4.json
Normal file
80
output-reports/eval_report_v1_shard1of4.json
Normal file
@@ -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)."
|
||||
}
|
||||
80
output-reports/eval_report_v1_shard2of4.json
Normal file
80
output-reports/eval_report_v1_shard2of4.json
Normal file
@@ -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)."
|
||||
}
|
||||
80
output-reports/eval_report_v1_shard3of4.json
Normal file
80
output-reports/eval_report_v1_shard3of4.json
Normal file
@@ -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)."
|
||||
}
|
||||
80
output-reports/eval_report_v1_shard4of4.json
Normal file
80
output-reports/eval_report_v1_shard4of4.json
Normal file
@@ -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)."
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||
size 11422650
|
||||
29
tokenizer_config.json
Normal file
29
tokenizer_config.json
Normal file
@@ -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
|
||||
}
|
||||
Reference in New Issue
Block a user