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
2026-06-17 19:15:16 +08:00
commit 556e0dfc29
13 changed files with 232 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-BF16.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-IQ4_XS.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q2_K.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q3_K_M.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q3_K_S.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q4_K_M.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q4_K_S.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q5_K_M.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q5_K_S.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q6_K.gguf
+++ 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
--- a/LFM2.5-8B-A1B-Uncensored-Q8_0.gguf
+++ 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
--- a/README.md
+++ 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