lm-eval

Here are 5 public repositories matching this topic...

Blackwellboy / model-serving-minefield

Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant kernel paths, CUDA toolchains, KV allocation, eval harnesses, versioning. Symptom-first, with the check that catches each.

debugging benchmarking cuda quantization troubleshooting model-evaluation chat-template llm-serving llama-cpp vllm local-llm speculative-decoding reasoning-models lm-eval

Updated Aug 19, 2026
Python

Jojodicus / ai-identity-benchmark

Star

Does the identity in a system prompt change performance?

python benchmarking benchmark ai ai-agents uv ai-agent lm-evaluation-harness lm-eval

Updated Mar 3, 2026
Python

imanshrajsingh-boost / qwen2.5-coder-finetuning-qlora-dpo

Star

Fine-tuning pipeline for Qwen2.5-Coder-1.5B using QLoRA, DPO alignment, and AWQ quantization on free-tier Colab GPU.

python code python3 lora fine-tuning finetuning sft dpo huggingface huggingface-transformers awq llm lm-evaluation-harness bitsandbytes finetuning-llms awq-quantization qwen2-5-coder lm-eval lm-eval-harness

Updated Aug 19, 2026
Jupyter Notebook

yinli-systems / l20-edu-135m-pretrain

Star

From-scratch 135M Transformer pretraining on 10B FineWeb-Edu tokens using a single NVIDIA L20, with public checkpoint and lm-eval comparisons.

pytorch transformer reproducibility pretraining l20 llm-training lm-eval fineweb-edu

Updated Jun 27, 2026
Python

ailiance / ailiance-bench

Star

Benchmarking MLX pour modèles open-source et fine-tunes Ailiance (gsm8k, arc, mmlu_pro, perplexité 5 niches)

benchmark mlx apple-silicon eu-ai-act lm-eval ailiance lora-evaluation

Updated May 21, 2026
Python

Improve this page

Add a description, image, and links to the lm-eval topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the lm-eval topic, visit your repo's landing page and select "manage topics."

Learn more