commit 11f4b9ee9a7c6600c58172d6669bddca04fed0bb Author: ModelHub XC Date: Wed Jul 29 02:26:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: gauthierpiarrette/nl2jq-qwen3-0.6b Source: Original Platform 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..920f939 --- /dev/null +++ b/README.md @@ -0,0 +1,112 @@ +--- +license: apache-2.0 +language: +- en +pipeline_tag: text-generation +base_model: Qwen/Qwen3-0.6B +tags: +- jq +- code-generation +- json +- lora +datasets: +- gauthierpiarrette/nl2jq +metrics: +- execution-accuracy +--- + +# nl2jq-qwen3-0.6b + +*Part of the **nl2jq** project — [all artifacts](https://huggingface.co/collections/gauthierpiarrette/nl2jq-natural-language-to-jq-locally-6a5299203df3832415275223) · [code + CLI](https://github.com/gauthierpiarrette/nl2jq) · [live demo](https://huggingface.co/spaces/gauthierpiarrette/nl2jq) · [benchmark](https://huggingface.co/datasets/gauthierpiarrette/nl2jq-bench)* + +A LoRA fine-tune of [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) that translates a +natural-language request plus a JSON sample into a [jq](https://jqlang.github.io/jq/) +program. It is the **practical baseline** companion to the from-scratch +[`nl2jq-40m`](https://huggingface.co/gauthierpiarrette/nl2jq-40m): larger, but its +pretrained language priors make it markedly more reliable at **copying novel field names** +from your JSON — which is what most real CLI use needs. + +The LoRA adapter has been merged into the base weights, so it loads as an ordinary model. + +**This is the recommended default backend of the `jqgen` CLI** — the best +latency/accuracy balance for local use (~1–3s per query on laptop CPU). + +## Usage + +```bash +cat data.json | jqgen --backend qwen "total spend per customer, paid orders only" +``` + +Or directly: +```python +import re +from transformers import AutoModelForCausalLM, AutoTokenizer + +tok = AutoTokenizer.from_pretrained("gauthierpiarrette/nl2jq-qwen3-0.6b") +model = AutoModelForCausalLM.from_pretrained("gauthierpiarrette/nl2jq-qwen3-0.6b") +msgs = [{"role": "system", "content": "You translate a natural-language request plus a " + "sample of JSON into a single jq program. Output only the jq program, nothing else."}, + {"role": "user", "content": "Request: highest paid person\nJSON sample: [...]"}] +enc = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt") +ids = enc["input_ids"] # newer transformers return a BatchEncoding here, not a tensor +out = tok.decode(model.generate(ids, max_new_tokens=128)[0][ids.shape[1]:], + skip_special_tokens=True) +# Qwen3 emits an (empty) reasoning block before the program — strip it: +print(re.sub(r"(?s)^\s*.*?\s*", "", out).strip()) +``` + +## Results + +Execution accuracy on the frozen 400-item +[`nl2jq-bench v1.0.0`](https://huggingface.co/datasets/gauthierpiarrette/nl2jq-bench) +(0% field overlap with training, novel domains, one-shot evaluation). **These weights are +the v6 fine-tune** — trained on data with per-example-unique field names and coverage of +`reduce`/`foreach`/`walk`/`paths`/`if` constructs; the superseded v5 row is kept for the +record: + +| Model | frozen pass@1 | valid | T1 | T2 | T3 | T4 | T5-gen | +|---|---|---|---|---|---|---|---| +| **this model (v6)** | **0.40** | 0.73 | 0.65 | 0.52 | 0.36 | 0.28 | **0.20** | +| v5 fine-tune (superseded) | 0.24 | 0.67 | 0.45 | 0.38 | 0.21 | 0.12 | 0.02 | +| Qwen3-0.6B base (zero-shot) | 0.01 | 0.06 | 0.02 | 0.00 | 0.00 | 0.00 | 0.02 | +| [nl2jq-qwen3.5-2b](https://huggingface.co/gauthierpiarrette/nl2jq-qwen3.5-2b) (bigger sibling, CLI config) | 0.48 | 0.82 | 0.75 | 0.61 | 0.47 | 0.35 | 0.18 | +| Claude Opus 4.8 (zero-shot, context row) | 0.96 | 0.98 | 1.00 | 0.96 | 0.96 | 0.96 | 0.90 | + +Three honest readings: + +- **Fine-tuning does all the work at this scale**: the base model zero-shot scores 0.01 + (it emits pseudo-code, not jq); this LoRA takes it to 0.40 on held-out fields. +- **The v6 data fix mattered more than anything else**: same base, same LoRA recipe, + +67% pass@1 and 10× T5 purely from making field-copying the only winning strategy in + training. +- **This is the fast backend, not the most accurate one**: it answers in ~1–3s on laptop + CPU; the 2B sibling is +8 points at ~3× the latency. Both remain far from the frontier's + 0.96 — that gap is disclosed, not hidden. + +## Training + +- **Base**: Qwen3-0.6B. **Method**: LoRA (r=32, α=64, all-linear targets), 1 epoch over + 150k execution-verified examples, cosine schedule, bf16, gradient checkpointing. +- **Data**: the v6 generation of the synthetic pipeline — per-example-unique field names + (so copying from the input, not vocabulary recall, is the only winning strategy) plus + generators for `reduce`/`foreach`/`walk`/`paths`/`if`-banding constructs. 100% synthetic + and execution-verified — see the + [nl2jq dataset](https://huggingface.co/datasets/gauthierpiarrette/nl2jq). No web text, no + scraped code. Every program was run under jq 1.7.1 and kept only if it produced + non-degenerate output. +- Frontier-model outputs are **never** used as training targets; all natural-language + phrasings are template/grammar-generated by the author. + +## Limitations + +- jq 1.7.1 only; no streaming, modules, or user-defined functions. +- Ambiguous requests may yield a valid program that answers a different reading. +- **Inspect before trusting the output** — the `jqgen` CLI prints the program to stderr. + jq runs locally with no network access, but an incorrect program can still mislead. +- Not a general assistant — it emits jq and nothing else. + +## License + +Apache-2.0 (inherits the base model's license). Fine-tuned on CC BY 4.0 synthetic data. + +Code, benchmark tooling, and training pipeline: [github.com/gauthierpiarrette/nl2jq](https://github.com/gauthierpiarrette/nl2jq) 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..95dafa4 --- /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": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "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": "5.13.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..22e647d --- /dev/null +++ b/eval_results.json @@ -0,0 +1,25 @@ +{ + "benchmark": "gauthierpiarrette/nl2jq-bench", + "version": "1.0.0", + "freeze_sha256": "25e7c01360707b30df93e7c1ed26997b3bb3ee7840a093d024bb4d16f489c5de", + "jq_version": "1.7.1", + "n_items": 400, + "protocol": "one-shot; no selection or iteration against the frozen set", + "model": "gauthierpiarrette/nl2jq-qwen3-0.6b", + "results": [ + { + "system": "nl2jq-qwen3-0.6b-v6", + "decoding": "greedy", + "pass_at_1": 0.4, + "valid_at_1": 0.73, + "tiers": { + "T1": 0.65, + "T2": 0.52, + "T3": 0.36, + "T4": 0.28, + "T5": 0.2 + }, + "t5_generalization": 0.2 + } + ] +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8df7a2c --- /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": "5.13.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..700a17d --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9f227b582c165fd64dd7c090646c9617c814e5268d84226576701ee28eba41 +size 1192135096 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..9a87e38 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "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, + "local_files_only": true, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}