datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
awq-model-zoootto-taxonomy-sdg-mistral-small-24b-instruct-2501-awqrocm-vlm-ocr-awq-configs
ROCm VLM/OCR AWQ+BF16 Serving Config Bundle
A4 @ 200 DPI coverage verified (max_model_len >= 8192, visual tokens ~3800 + text ~4096).
Model Profiles
Profile
Model
Quant
max_model_len
Concurrent VRAM
vllm-qwen3-vl-awq.json
cyankiwi/Qwen3-VL-8B-Instruct-AWQ-4bit
AWQ W4A16
8192
0.30
vllm-bizonai-bf16.json
ONTHEIT/BizOnAI-OCR
BF16
8192
0.26
sglang-qwen3-vl-awq.json
cyankiwi/Qwen3-VL-8B-Instruct-AWQ-4bit
AWQ W4A16
8192
0.30
A4 @ 200 DPI Token… See the full description on the dataset page: https://huggingface.co/datasets/yakdoli/rocm-vlm-ocr-awq-configs.all-Meta-Llama-3.1-70B-Instruct-AWQ-INT4details_maldv__Awqward2.5-32B-Instruct_v2
Dataset Card for Evaluation run of maldv/Awqward2.5-32B-Instruct
Dataset automatically created during the evaluation run of model maldv/Awqward2.5-32B-Instruct.
The dataset is composed of 116 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_maldv__Awqward2.5-32B-Instruct_v2.all-Qwen2.5-72B-Instruct-AWQnortonstories-mistral-7b-instruct-v0-2-awqQwen3.5-27B-AWQ-4bit-GPQA-Diamond-benchmarkBenchmark of cyankiwi/Qwen3.5-27B-AWQ-4bit against fingertap/GPQA-Diamond dataset.
Accuracy: 76.3% with Python tool.
Metric
Value
Correct
151
Incorrect
46
Errors
1
Total samples
198
Python tool calls
225
Total completion tokens
659,879
Raw stats:
{
"accuracy": 0.763,
"correct": 151,
"incorrect": 46,
"error": 1,
"total": 198,
"python_tool_calls": 225,
"completion_tokens": 659879
}
awq-model-zoo
yujiepan/awq-model-zoo
Here are some pre-computed awq information (scales & clips) used in llm-awq.
Scripts
Install the forked llm-awq at https://github.com/yujiepan-work/llm-awq/tree/a41a08e79d8eb3d6335485b3625410af22a74426. Note: works with transformers==4.35.2
Generating awq-info.pt:
python do_awq.py --model_id mistralai/Mistral-7B-v0.1 --w_bit 8 --q_group_size 128 --dump_awq ./awq-info.pt
Load a quantized model: You can use the offical repo to get a fake/real… See the full description on the dataset page: https://huggingface.co/datasets/yujiepan/awq-model-zoo.dreambench_eval_results_internvl2_5_78b_mpo_awq_init_1_prompt_collect_training_dataLlama-3.3-70B-Inst-awq_SafeRLHF
Llama-3.3-70B-Inst-awq Responses for RefAlign Safety Alignment
This dataset contains responses generated for the paper Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data, which introduces the RefAlign alignment algorithm.
Code Repository: https://github.com/mzhaoshuai/RefAlign
This dataset specifically consists of responses generated by the casperhansen/llama-3.3-70b-instruct-awq model, given the prompts from the… See the full description on the dataset page: https://huggingface.co/datasets/mzhaoshuai/Llama-3.3-70B-Inst-awq_SafeRLHF.internlm-xcomposer2-7b-awq3090-Qwen3-8B-AWQ-metricspileval_awq_datasetdetails_TheBloke__Llama-2-7b-Chat-AWQ
Dataset Card for Evaluation run of TheBloke/Llama-2-7b-Chat-AWQ
Dataset Summary
Dataset automatically created during the evaluation run of model TheBloke/Llama-2-7b-Chat-AWQ on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_TheBloke__Llama-2-7b-Chat-AWQ.swesmith-glm5-awq-traces-10kqwen3.5-moe-awq-calibration
Qwen3.5 MoE AWQ Calibration Dataset
Calibration dataset for AWQ (Activation-Aware Weight Quantization) of
Qwen/Qwen3.5-35B-A3B and
Qwen/Qwen3.5-35B-A3B-Base.
Designed for MoE expert routing diversity: Qwen3.5-35B-A3B has 256 experts with 8
active per token, so calibration data needs broad domain coverage to exercise as many
routing paths as possible.
Sampling methodology
Source: PleIAs/common_corpus
(open multi-domain corpus with labeled collections)
Filtering:
Token… See the full description on the dataset page: https://huggingface.co/datasets/Lambent/qwen3.5-moe-awq-calibration.en_awq_datasetxh_wikipedia_awq_datasetLlama-3.3-70B-Inst-awq_ultrafeedback_1in3
Generated Reference Answers for Language Model Alignment
This dataset contains responses generated for the research presented in the paper Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data.
The paper introduces RefAlign, a versatile REINFORCE-style alignment algorithm that utilizes language generation evaluation metrics, such as BERTScore, between sampled generations and reference answers as surrogate rewards. This approach… See the full description on the dataset page: https://huggingface.co/datasets/mzhaoshuai/Llama-3.3-70B-Inst-awq_ultrafeedback_1in3.clinical-pl-smpc-awq-calibration
Clinical-PL SmPC AWQ Calibration Corpus
A Polish clinical-domain text corpus used as the calibration set for AWQ / AutoAWQ
quantization of the Llama-PLLuM-70B model family. The corpus is dense, domain-specific
clinical Polish (pulmonology + thoracic oncology), chosen as activation-aware
quantization calibration data for models intended for clinical-Polish use.
Used to calibrate the mozarcik/Llama-PLLuM-70B-*-awq family (8 variants, AMD
Developer Cloud / Instinct MI300X… See the full description on the dataset page: https://huggingface.co/datasets/mozarcik/clinical-pl-smpc-awq-calibration.chatbot-arena-ja-karakuri-lm-8x7b-chat-v0.1-awqchatbot-arena-ja-calm2-7b-chatをフィルタリングし、karakuri-lm-8x7b-chat-v0.1-awqでchosenを生成しました
sw_awq_datasetswesmith-glm5-awq-traces-10kterminal_bench_2_swesmith_glm5_awq_20260414_044534fr_awq_datasetsw_awq_dataset_codesterminal_bench_2_swesmith_glm5_awq_traces_10k_tacc_20260415_185725clinical-en-smpc-awq-calibration
Clinical-EN SmPC AWQ Calibration Corpus
An English clinical-domain text corpus used as a calibration set for AWQ / AutoAWQ /
GPTQ post-training quantization of English (or multilingual) clinical large language
models. The corpus is dense, domain-specific clinical English (pulmonology + thoracic
oncology), drawn from the English Summary of Product Characteristics (SmPC, Annex I
of the EMA Product Information).
This is the cross-language counterpart to the Polish corpus… See the full description on the dataset page: https://huggingface.co/datasets/mozarcik/clinical-en-smpc-awq-calibration.xh_awq_dataset_math