commit 556e0dfc29ccd92f652228db3a17120274542517 Author: ModelHub XC Date: Wed Jun 17 19:15:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: zaakirio/LFM2.5-8B-A1B-Uncensored-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a07cef6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +LFM2.5-8B-A1B-Uncensored-BF16.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Uncensored-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-8B-A1B-Uncensored-BF16.gguf b/LFM2.5-8B-A1B-Uncensored-BF16.gguf new file mode 100644 index 0000000..f8f6561 --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7260abf4ec6ce889c676a517f080b965458fcf0f7e42edb659c5d808b24a3cd3 +size 16947260096 diff --git a/LFM2.5-8B-A1B-Uncensored-IQ4_XS.gguf b/LFM2.5-8B-A1B-Uncensored-IQ4_XS.gguf new file mode 100644 index 0000000..319ef3a --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4703e9bcce9c103982d6dfbcf99edb3de9ff1c70acacc0de6f40ff3283e940c1 +size 4611238592 diff --git a/LFM2.5-8B-A1B-Uncensored-Q2_K.gguf b/LFM2.5-8B-A1B-Uncensored-Q2_K.gguf new file mode 100644 index 0000000..b8697a0 --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccc1eaf0b1b8caec64885ed61ef6f1a8d5744bcccd86c576593a392f1abea15 +size 3190434496 diff --git a/LFM2.5-8B-A1B-Uncensored-Q3_K_M.gguf b/LFM2.5-8B-A1B-Uncensored-Q3_K_M.gguf new file mode 100644 index 0000000..4ad4212 --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3b7b99bf6749c838a3c8b86952d2e7279a18aaadfe44374f04441a68205e8c8 +size 4108397248 diff --git a/LFM2.5-8B-A1B-Uncensored-Q3_K_S.gguf b/LFM2.5-8B-A1B-Uncensored-Q3_K_S.gguf new file mode 100644 index 0000000..c4a8555 --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ccc111c1543d22eb4718e029f91c9fd447448e172680cd208b4fc6ffc1b0252 +size 3755076288 diff --git a/LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf b/LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf new file mode 100644 index 0000000..a79944a --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66e45364a735cf9c187a8c2456d2620801daec21a749a953de3d9b214a207c0 +size 5155564224 diff --git a/LFM2.5-8B-A1B-Uncensored-Q4_K_S.gguf b/LFM2.5-8B-A1B-Uncensored-Q4_K_S.gguf new file mode 100644 index 0000000..14e8500 --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1685bb67d0d1cc8338b3f2c1bce61e13d685ed1793b678f527859f0e5a870e90 +size 4863552192 diff --git a/LFM2.5-8B-A1B-Uncensored-Q5_K_M.gguf b/LFM2.5-8B-A1B-Uncensored-Q5_K_M.gguf new file mode 100644 index 0000000..3485494 --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2315661d1bfc0745f6f36113b5e914019f473b7c65bebd6e657f871aabd1591c +size 6030338752 diff --git a/LFM2.5-8B-A1B-Uncensored-Q5_K_S.gguf b/LFM2.5-8B-A1B-Uncensored-Q5_K_S.gguf new file mode 100644 index 0000000..c772e8c --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48745f0af814b975d5e0dd6ae6c8de708cbc75c8ee9b4c92520ea05befd521aa +size 5870185152 diff --git a/LFM2.5-8B-A1B-Uncensored-Q6_K.gguf b/LFM2.5-8B-A1B-Uncensored-Q6_K.gguf new file mode 100644 index 0000000..b1079cf --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43042a23d85093be0a0987a3a62288f886d7817a72bd70b08b4de849968e6b8 +size 6959786688 diff --git a/LFM2.5-8B-A1B-Uncensored-Q8_0.gguf b/LFM2.5-8B-A1B-Uncensored-Q8_0.gguf new file mode 100644 index 0000000..d8b6ae0 --- /dev/null +++ b/LFM2.5-8B-A1B-Uncensored-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4193ed1ac302c7758ff0c4158eac519679b88769a3f783dfd83ac4c82b296f92 +size 9010195136 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c8f95d8 --- /dev/null +++ b/README.md @@ -0,0 +1,153 @@ +--- +base_model: zaakirio/LFM2.5-8B-A1B-Uncensored +base_model_relation: quantized +quantized_by: zaakirio +license: other +license_name: lfm1.0 +license_link: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B/blob/main/LICENSE +library_name: gguf +pipeline_tag: text-generation +language: +- en +- ar +- zh +- fr +- de +- ja +- ko +- es +- pt +tags: +- heretic +- abliterated +- decensored +- uncensored +- liquid +- lfm2 +- lfm2.5 +- moe +- edge +- gguf +- llama.cpp +- conversational +--- + +# LFM2.5-8B-A1B-Uncensored — GGUF + +GGUF quantizations of [`zaakirio/LFM2.5-8B-A1B-Uncensored`](https://huggingface.co/zaakirio/LFM2.5-8B-A1B-Uncensored), +a decensored ([Heretic](https://github.com/p-e-w/heretic)-abliterated) version of +[`LiquidAI/LFM2.5-8B-A1B`](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B). + +These files run with [llama.cpp](https://github.com/ggml-org/llama.cpp) and any +tool built on it e.g. **Ollama**, **LM Studio**, **textgen**, etc. + +> **Requires a recent llama.cpp build with LFM2 MoE support.** This model uses +> the `lfm2moe` architecture (hybrid short-conv + attention with 32 experts, +> 4 active per token). Only llama.cpp builds that include `Lfm2MoeForCausalLM` +> support can load these files. Use a current release (or current Ollama / +> LM Studio). Older builds will fail with an "unknown architecture 'lfm2moe'" +> error. + +## Files + +| File | Quant | Size | BPW | Notes | +|---|---|---|---|---| +| `LFM2.5-8B-A1B-Uncensored-Q2_K.gguf` | Q2_K | 3.0 GB | 3.01 | Smallest; significant quality loss but works on very constrained hardware. | +| `LFM2.5-8B-A1B-Uncensored-Q3_K_S.gguf` | Q3_K_S | 3.5 GB | 3.54 | Small, lower quality. | +| `LFM2.5-8B-A1B-Uncensored-Q3_K_M.gguf` | Q3_K_M | 3.9 GB | 3.87 | Small; some quality loss. | +| `LFM2.5-8B-A1B-Uncensored-IQ4_XS.gguf` | IQ4_XS | 4.3 GB | 4.25 | Smaller than Q4_K_S with comparable quality; uses iquant scheme. | +| `LFM2.5-8B-A1B-Uncensored-Q4_K_S.gguf` | Q4_K_S | 4.6 GB | 4.59 | Slightly smaller than Q4_K_M. | +| `LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf` | Q4_K_M | 4.9 GB | 4.85 | **Recommended** — best size/quality balance for most users. | +| `LFM2.5-8B-A1B-Uncensored-Q5_K_S.gguf` | Q5_K_S | 5.5 GB | 5.49 | Higher quality. | +| `LFM2.5-8B-A1B-Uncensored-Q5_K_M.gguf` | Q5_K_M | 5.7 GB | 5.69 | Higher quality, marginally larger. | +| `LFM2.5-8B-A1B-Uncensored-Q6_K.gguf` | Q6_K | 6.5 GB | 6.56 | Near-lossless. | +| `LFM2.5-8B-A1B-Uncensored-Q8_0.gguf` | Q8_0 | 8.4 GB | 8.50 | Effectively lossless vs the BF16 source. | +| `LFM2.5-8B-A1B-Uncensored-BF16.gguf` | BF16 | 16 GB | 16.00 | Full precision, identical numerics to the source HF model. | + +Not sure which to pick? Start with **Q4_K_M**. Go up to Q5/Q6/Q8 if you have +the memory and want maximum fidelity; drop to Q3 or Q2 only if you're memory-constrained. +Because this is an MoE with only ~1B active parameters per token, inference +throughput is fast even at the larger quants if your hardware has the RAM. + +## Usage + +### llama.cpp (auto-download from this repo) + +```bash +# Interactive chat — downloads the chosen quant automatically +llama-cli -hf zaakirio/LFM2.5-8B-A1B-Uncensored-GGUF:Q4_K_M + +# OpenAI-compatible server +llama-server -hf zaakirio/LFM2.5-8B-A1B-Uncensored-GGUF:Q4_K_M -c 4096 +``` + +Or, with a file you've already downloaded: + +```bash +llama-cli -m LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf -p "Hello, who are you?" +``` + +### Ollama + +```bash +ollama run hf.co/zaakirio/LFM2.5-8B-A1B-Uncensored-GGUF:Q4_K_M +``` + +### LM Studio / Jan + +Search for `zaakirio/LFM2.5-8B-A1B-Uncensored-GGUF` in the in-app model browser, +or download a `.gguf` file from this page and load it. + +### Download a single file + +```bash +pip install -U "huggingface_hub[cli]" +hf download zaakirio/LFM2.5-8B-A1B-Uncensored-GGUF \ + --include "LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf" --local-dir ./ +``` + +## Prompt format + +The chat template is embedded in the GGUF files, so chat-aware tools apply it +automatically. For reference, it is ChatML-style: + +``` +<|startoftext|><|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## About the base model + +This is a decensored derivative produced with [Heretic](https://github.com/p-e-w/heretic) +(automatic directional ablation). Compared with the original `LFM2.5-8B-A1B`: + +| Metric | Decensored | Original | +|---|---|---| +| Refusals (/100 harmful prompts) | 0 | 0 | +| KL divergence (harmless prompts) | 0.0481 | 0 (by definition) | + +The base `LFM2.5-8B-A1B` measured 0–2 / 100 refusals on Heretic's marker-based +detector (compared to ~98 / 100 for its smaller sibling), suggesting it is +comparatively compliant out of the box. The abliteration still makes real, +measurable changes to the attention and dense MLP projections (KL ≈ 0.05). + +See the [source model card](https://huggingface.co/zaakirio/LFM2.5-8B-A1B-Uncensored) +for the full abliteration parameters and run details. + +## Intended use & disclaimer + +This model has had its refusal behavior substantially removed and will comply +with requests the original model would have declined. It is provided for +research and unrestricted local use. **You are responsible for how you use it** +and for complying with all applicable laws and with the base model's +[lfm1.0 license](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B/blob/main/LICENSE), +which carries over to this derivative. + +## Provenance + +- Quantized from `zaakirio/LFM2.5-8B-A1B-Uncensored` (BF16) using llama.cpp `convert_hf_to_gguf.py` + `llama-quantize`. +- Base model: [LiquidAI/LFM2.5-8B-A1B](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) +- Decensoring tool: [Heretic](https://github.com/p-e-w/heretic) by p-e-w