ModelHub XC eb75795ee0 初始化项目,由ModelHub XC社区提供模型
Model: jgalego/ada-coder-qwen2.5-7b
Source: Original Platform
2026-11-14 14:13:43 +08:00

base_model, datasets, language, library_name, license, pipeline_tag, tags, model-index
base_model datasets language library_name license pipeline_tag tags model-index
Qwen/Qwen2.5-Coder-7B-Instruct
the-clanker-lover/steelman-sft-ada
nuprl/MultiPL-E
en transformers apache-2.0 text-generation
ada
spark
code
name results
ada-coder-qwen2.5-7b
task dataset metrics
type
text-generation
name type config
MultiPL-E HumanEval-Ada nuprl/MultiPL-E humaneval-adb
type value name
pass@1 0.414 pass@1
type value name
compile_rate 0.771 Compile rate

ada-coder-qwen2.5-7b

Ada coder logo: a Jacquard punched card, after Ada Lovelace's loom analogy, whose holes form a teal check mark

Qwen/Qwen2.5-Coder-7B-Instruct fine-tuned with LoRA to write Ada 2022 and SPARK code from a task description, spec or signature.

Warning

Review every line. The output is not qualified for DO-178C, EN 50128, ISO 26262 or any other certification process. Compile it, test it and, for SPARK, prove it before use.

🚀 Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "jgalego/ada-coder-qwen2.5-7b"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, dtype="auto")

messages = [
    {"role": "system", "content": "You write Ada 2022 and SPARK code that compiles cleanly with GNAT."},
    {"role": "user", "content": "Write a function that returns the greatest common divisor of two Positive numbers."},
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True,
)
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))

It also completes raw Ada source with no chat template, which is how it is scored below.

🏋️ Training

Base Qwen/Qwen2.5-Coder-7B-Instruct
Data r7_dataset.jsonl from the-clanker-lover/steelman-sft-ada, 6,110 instruction/code pairs that compile with GNAT
Method LoRA, r=16, alpha=32, all linear layers, merged
Steps 378 (1.0 epochs), batch size 16, max length 2048
Learning rate 0.0002, cosine
Mean train loss 0.2128
Hardware NVIDIA A10G, 69 min

📊 Results

nuprl/MultiPL-E HumanEval-Ada (humaneval-adb, 157 problems). Greedy decoding from the raw prompt, then built and run with the GNAT flags from MultiPL-E's eval_adb.py. A program passes when every pragma Assert holds.

Model n pass@1 Compile rate Runtime errors Timeouts
jgalego/ada-coder-qwen2.5-7b 157 0.414 0.771 56 0
jgalego/ada-coder-qwen2.5-7b@grpo-1 157 0.414 0.796 60 0
jgalego/ada-coder-qwen2.5-7b@sft-2 157 0.401 0.771 58 0
Qwen/Qwen2.5-Coder-7B-Instruct 157 0.312 0.471 25 0

Reference scores reported by the Steelman authors (model card, report) on the same benchmark with their own harness, temperature 0:

Model pass@1 Compile rate
Steelman 14B v0.3 (Qwen2.5-Coder-14B + R7 data) 0.459 0.854
Steelman 14B v0.2 (Qwen2.5-Coder-14B-Instruct + R6 data) 0.471 0.752
Qwen2.5-Coder-14B, untuned 0.344 0.510

⚠️ Limitations

  • Scored on small HumanEval-style functions, not on full programs or packages.
  • Contracts are at most checked at run time (-gnata); nothing here runs GNATprove.
  • Trained on a single dataset; style follows that data.
S
Description
Model synced from source: jgalego/ada-coder-qwen2.5-7b
Readme
137 KiB
0 Stars 1 Watchers 0 Forks
Languages
Jinja 100%