**This is the full Chinese-LLaMA-2-13B model,which can be loaded directly for inference and full-parameter training.** **Related models👇** * Long context base models * Chinese-LLaMA-2-7B-16K (full model) * Chinese-LLaMA-2-LoRA-7B-16K (LoRA model) * Chinese-LLaMA-2-13B-16K (full model) * Chinese-LLaMA-2-LoRA-13B-16K (LoRA model) * Base models * Chinese-LLaMA-2-7B (full model) * Chinese-LLaMA-2-LoRA-7B (LoRA model) * Chinese-LLaMA-2-13B (full model) * Chinese-LLaMA-2-LoRA-13B (LoRA model) * Instruction/Chat models * Chinese-Alpaca-2-7B (full model) * Chinese-Alpaca-2-LoRA-7B (LoRA model) * Chinese-Alpaca-2-13B (full model) * Chinese-Alpaca-2-LoRA-13B (LoRA model) This project is based on the Llama-2, released by Meta, and it is the second generation of the Chinese LLaMA & Alpaca LLM project. We open-source Chinese LLaMA-2 (foundation model) and Alpaca-2 (instruction-following model). These models have been expanded and optimized with Chinese vocabulary beyond the original Llama-2. We used large-scale Chinese data for incremental pre-training, which further improved the fundamental semantic understanding of the Chinese language, resulting in a significant performance improvement compared to the first-generation models. The relevant models support a 4K context and can be expanded up to 18K+ using the NTK method.
**This is the full Chinese-LLaMA-2-13B-16K (context size 16K),model,which can be loaded directly for inference and full-parameter training.** **Related models👇** * Long context base models (16K) * Chinese-LLaMA-2-7B-16K (full model) * Chinese-LLaMA-2-LoRA-7B-16K (LoRA model) * Chinese-LLaMA-2-13B-16K (full model) * Chinese-LLaMA-2-LoRA-13B-16K (LoRA model) * Long context Instruction/Chat models * Chinese-Alpaca-2-7B-16K (full model) * Chinese-Alpaca-2-LoRA-7B-16K (LoRA model) * Chinese-Alpaca-2-13B-16K (full model) * Chinese-Alpaca-2-LoRA-13B-16K (LoRA model) * Base models * Chinese-LLaMA-2-7B (full model) * Chinese-LLaMA-2-LoRA-7B (LoRA model) * Chinese-LLaMA-2-13B (full model) * Chinese-LLaMA-2-LoRA-13B (LoRA model) * Instruction/Chat models * Chinese-Alpaca-2-7B (full model) * Chinese-Alpaca-2-LoRA-7B (LoRA model) * Chinese-Alpaca-2-13B (full model) * Chinese-Alpaca-2-LoRA-13B (LoRA model) This project is based on the Llama-2, released by Meta, and it is the second generation of the Chinese LLaMA & Alpaca LLM project. We open-source Chinese LLaMA-2 (foundation model) and Alpaca-2 (instruction-following model). These models have been expanded and optimized with Chinese vocabulary beyond the original Llama-2. We used large-scale Chinese data for incremental pre-training, which further improved the fundamental semantic understanding of the Chinese language, resulting in a significant performance improvement compared to the first-generation models. The relevant models support a 4K context and can be expanded up to 18K+ using the NTK method.
This repository contains **Chinese-Mixtral-Instruct**, which is further tuned with instruction data on Chinese-Mixtral, where Chinese-Mixtral is build on top of Mixtral-8x7B-v0.1. Please consider cite our paper if you use the resource of this repository. Paper link: https://arxiv.org/abs/2403.01851
This repository contains **Llama-3-Chinese-8B-Instruct**, which is further tuned with 5M instruction data on Llama-3-Chinese-8B. Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3
This repository contains **Llama-3-Chinese-8B-Instruct-v2**, which is directly tuned with 5M instruction data on Meta-Llama-3-8B-Instruct. Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3
This repository contains **Llama-3-Chinese-8B-Instruct-v3**, which is further finetuned based on a mix of the following models: - hfl/Llama-3-Chinese-8B-Instruct - hfl/Llama-3-Chinese-8B-Instruct-v2 - meta-llama/Meta-Llama-3-8B-Instruct Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3
> **🚧 PREVIEW RELEASE (v0.1) — feedback wanted.** > This is an early preview of a quant-native abliteration of the Bonsai 2 pack. The > numbers below are from my own small harness, so I would rather have the community > poke at it than call it finished. Please open a **Discussion** in the Community tab > with anything you find — good or bad. **Status: preview (v0.1) — not a final release.** A refusal-reduced build of **`prism-ml/Ternary-Bonsai-2-27B-gguf`** (PQ2_0, 2.13 bpw, 7.21 GB). The pack is edited **in its own deployed quantization format**: there is no BF16 dequantization anywhere in the pipeline and no re-quantization. The official pack's stored 2-bit codes were updated directly, in place, so the shipped artifact *is* the edited pack: same geometry, same size, same kernel path, no runtime hook, no adapter. A full-precision refusal-free reference of the same base family was used only to define *what* to change; that change was then written onto the pack's existing quantization lattice with an **unbiased** code-rounding schedule, so that the *expected* weight movement equals the intended edit even though each individual code can only move in whole lattice steps. The edit was amplitude-swept and selected on measured behaviour.
> Hard-convert **38/40** on a fixed harmful pilot while keeping coding near the parent — not a max-HC-only scar model. Optional speculative decode: use Prism’s official **DSpark** drafter unchanged (`Ternary-Bonsai-27B-dspark-Q4_1.gguf` from the base repo). Accept-rate A/B on this weight vs parent: **≈1.00×** (n=30, CI overlap) → no draft retrain needed. 1. Residual / direction code-edit on ternary writers over the parent Q2_0 pack 2. Escalate to a high hard-convert seed (`esc-ALL-f65`) 3. **Seed-stage surgical rollback**: restore parent bytes on selected **L0–7 writers** (minimal mask `minM23`, ~1.5 MB changed vs full L0–7 rollback) 4. Gate on paired harmful eval + capability pilots; keep low-degradation winner
An **integrated MTP (Multi-Token Prediction) GGUF** build of the abliterated `Qwen3.8-Flash-Next-Uncensored` model, quantized to **Q4_K_M** with the MTP draft head **merged into the same 4-shard split** — no sidecar file needed. This model is an **abliterated (refusal-removed)** build. It will comply with harmful, unethical, or illegal requests the original `Qwen3.8-Flash-Next` would refuse. Released **strictly for legitimate research** — interpretability, AI-safety / refusal-mechanism study, red-teaming, and robustness evaluation. **You assume full responsibility** for how you use it and everything it generates; add your own safety and moderation layers before any deployment. **Qwen Community License 1.0** (see LICENSE), inherited from the base model `Qwen/Qwen3.8-Flash-Next`. Abliteration and quantization do not change the underlying license obligations.