初始化项目，由ModelHub XC社区提供模型

Model: unsloth/LFM2.5-8B-A1B-GGUF Source: Original Platform
2026-06-10 12:34:18 +08:00
commit b0505dfd9c
25 changed files with 410 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,58 @@
 *.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-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
 imatrix_unsloth.gguf_file filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-BF16.gguf filter=lfs diff=lfs merge=lfs -text
 LFM2.5-8B-A1B-UD-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
--- a/LFM2.5-8B-A1B-BF16.gguf
+++ b/LFM2.5-8B-A1B-BF16.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:bc9c40afbdbeb0bbc764f52c7d0b0088701fdecc78668c92ebc0a89e4a463bbe
 size 16947260768
--- a/LFM2.5-8B-A1B-MXFP4_MOE.gguf
+++ b/LFM2.5-8B-A1B-MXFP4_MOE.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:f4aeaba50cc24bf677aaa0cf75d0410e963195d2202390c5c9706e7f51ee839a
 size 5348437600
--- a/LFM2.5-8B-A1B-Q8_0.gguf
+++ b/LFM2.5-8B-A1B-Q8_0.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:ec11666b6129f0b4fe893760b66797f22e1c478a561b40e365f2b6930729b8d2
 size 9010196064
--- a/LFM2.5-8B-A1B-UD-IQ1_M.gguf
+++ b/LFM2.5-8B-A1B-UD-IQ1_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:4ea3c929fc1028d3564406c146e38938a47db166f0b5802350a785e4d7788e2b
 size 2573872736
--- a/LFM2.5-8B-A1B-UD-IQ2_M.gguf
+++ b/LFM2.5-8B-A1B-UD-IQ2_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:463670a7140a5d9e2a05f05afce1cd55e81ec764bbfd26e80287727d3e48645f
 size 2754588256
--- a/LFM2.5-8B-A1B-UD-IQ2_XXS.gguf
+++ b/LFM2.5-8B-A1B-UD-IQ2_XXS.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:99d381e0345d6a13721c9c0616c2bb45874b83a55e6a7689f8953f9369853730
 size 2701274720
--- a/LFM2.5-8B-A1B-UD-IQ3_S.gguf
+++ b/LFM2.5-8B-A1B-UD-IQ3_S.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:4a3c682957fa64e4361f651d6a157caaf8f2447bff64167eee0d258c0c937ef4
 size 3570921056
--- a/LFM2.5-8B-A1B-UD-IQ3_XXS.gguf
+++ b/LFM2.5-8B-A1B-UD-IQ3_XXS.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:f460496b7cf64a2cadc951e89884eb7509c0aae32f9f62062d42ebb415cfa675
 size 3272339040
--- a/LFM2.5-8B-A1B-UD-IQ4_NL.gguf
+++ b/LFM2.5-8B-A1B-UD-IQ4_NL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:a1921216ded964e5c4f787226729e8c2c32bd587ac7b897742e0b7a7cc7eff6a
 size 4358844000
--- a/LFM2.5-8B-A1B-UD-IQ4_XS.gguf
+++ b/LFM2.5-8B-A1B-UD-IQ4_XS.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:36a4f1c9fd045794e23978174aefda27971fdc2f257d6d032e3a26c047fe0eca
 size 4264996448
--- a/LFM2.5-8B-A1B-UD-Q2_K_XL.gguf
+++ b/LFM2.5-8B-A1B-UD-Q2_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:d5d1a7e009fe87e9f53ce2f2c8a6c8b07d560530837430085240be61055f8fed
 size 2925768288
--- a/LFM2.5-8B-A1B-UD-Q3_K_M.gguf
+++ b/LFM2.5-8B-A1B-UD-Q3_K_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:541ca0ed07d2d7977858f71ba32e3ab57aed27e1c9f1d54285a665026285e247
 size 3939626592
--- a/LFM2.5-8B-A1B-UD-Q3_K_XL.gguf
+++ b/LFM2.5-8B-A1B-UD-Q3_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:1cadae9f79eeffa38d950acc75a6e635ffec2372f6d8fee9c79f6ed05e714986
 size 4003114592
--- a/LFM2.5-8B-A1B-UD-Q4_K_M.gguf
+++ b/LFM2.5-8B-A1B-UD-Q4_K_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:e2c8350d5e6e7c633b2ba4e20805a2c86bc46884cd285e8f3fe36ad917b772c7
 size 5322223200
--- a/LFM2.5-8B-A1B-UD-Q4_K_S.gguf
+++ b/LFM2.5-8B-A1B-UD-Q4_K_S.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:ff96de1f5ec9b6ee4f78524fcce3955d3fae89413f58e993f30126587d9f4032
 size 5013941856
--- a/LFM2.5-8B-A1B-UD-Q4_K_XL.gguf
+++ b/LFM2.5-8B-A1B-UD-Q4_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:ee7c5e925a04cd672868959e48d199b66d6dcb9f90afe64f219856189e83b27e
 size 5351583328
--- a/LFM2.5-8B-A1B-UD-Q5_K_M.gguf
+++ b/LFM2.5-8B-A1B-UD-Q5_K_M.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:90e0b86095c6485fd5a9b7fa9822a02ebb103b6846f3eb3648643cea946fe9cf
 size 6361886304
--- a/LFM2.5-8B-A1B-UD-Q5_K_S.gguf
+++ b/LFM2.5-8B-A1B-UD-Q5_K_S.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:cf7d55ec2e0b427e152d31b08a5d7612472566efae7a2749064f507be9992c39
 size 6005894752
--- a/LFM2.5-8B-A1B-UD-Q5_K_XL.gguf
+++ b/LFM2.5-8B-A1B-UD-Q5_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:f4ae9cae33235d0e5e81f9bd399ea36bb2c9aff6e1a60d1885f6b535406ed33e
 size 6393081440
--- a/LFM2.5-8B-A1B-UD-Q6_K.gguf
+++ b/LFM2.5-8B-A1B-UD-Q6_K.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:f5c60637503fcbb479275b1bca9358a315ca5916556f1eeed40013da45a914c3
 size 7088287328
--- a/LFM2.5-8B-A1B-UD-Q6_K_XL.gguf
+++ b/LFM2.5-8B-A1B-UD-Q6_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:de2718c45e69587a0589ebe5f531ed4a99bccf341b2c122b6479ffe28929a9be
 size 7742467680
--- a/LFM2.5-8B-A1B-UD-Q8_K_XL.gguf
+++ b/LFM2.5-8B-A1B-UD-Q8_K_XL.gguf
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:3e3df81ea436475a727905f01968069f0d2b4bc361b831f10d9137b004c3c395
 size 9340497504
--- a/README.md
+++ b/README.md
@@ -0,0 +1,283 @@
 ---
 library_name: transformers
 license: other
 license_name: lfm1.0
 license_link: LICENSE
 language:
 - en
 - ar
 - zh
 - fr
 - de
 - ja
 - ko
 - es
 - pt
 pipeline_tag: text-generation
 tags:
 - liquid
 - unsloth
 - lfm2.5
 - edge
 base_model:
 - LiquidAI/LFM2.5-8B-A1B
 ---
 ## Updated from Liquid's chat template update
 <div>
 <p style="margin-top: 0;margin-bottom: 0;">
    <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
  </p>
  <div style="display: flex; gap: 5px; align-items: center; ">
    <a href="https://github.com/unslothai/unsloth/">
      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
    </a>
    <a href="https://discord.gg/unsloth">
      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
    </a>
    <a href="https://docs.unsloth.ai/">
      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
    </a>
  </div>
 </div>
 <div align="center">
  <img 
    src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" 
    alt="Liquid AI" 
    style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
  />
  <div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;">
    <a href="https://playground.liquid.ai/"><strong>Try LFM</strong></a> • 
    <a href="https://docs.liquid.ai/lfm/getting-started/welcome"><strong>Docs</strong></a> • 
    <a href="https://leap.liquid.ai/"><strong>LEAP</strong></a> • 
    <a href="https://discord.com/invite/liquid-ai"><strong>Discord</strong></a>
  </div>
 </div>
 # LFM2.5-8B-A1B
 LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
 - **On-device personal assistant**: Designed to power real-life applications, chaining tool calls, and following complex instructions on all devices.
 - **Compressed performance**: Competitive with much larger dense and MoE models on instruction following and agentic tasks.
 - **Unmatched throughput**: Fastest in its size class on both CPU and GPU inference, with day-one support for llama.cpp, MLX, vLLM, and SGLang.
 Find more information about LFM2.5-8B-A1B in our [blog post](https://www.liquid.ai/blog/lfm2-5-8b-a1b).
 ![image](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/qUZVGkns1bg3sZUShBbhv.png)
 **AA-Omniscience Index (higher is better) rewards correct answers and penalizes hallucinations. Scores range from -100 to 100. See more results on [Artificial Analysis](https://artificialanalysis.ai/evaluations/omniscience).*
 ## 🗒️ Model Details
 | Model | Parameters | Description |
 | --- | --- | --- |
 | [LFM2.5-8B-A1B-Base](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-Base) | 8.3B total / 1.5B active | Pre-trained base model for fine-tuning |
 | [**LFM2.5-8B-A1B**](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) | 8.3B total / 1.5B active | Reasoning-tuned general-purpose model |
 LFM2.5-8B-A1B is a general-purpose text-only model with the following features:
 - **Total parameters**: 8.3B
 - **Active parameters**: 1.5B
 - **Number of layers**: 24 (18 double-gated LIV conv + 6 GQA)
 - **Training budget**: 38 trillion tokens
 - **Context length**: 131,072
 - **Vocabulary size**: 128,000
 - **Languages**: English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, Spanish
 - **Generation parameters**: We recommend the following parameters:
  - `temperature: 0.2`
  - `top_k: 80`
  - `repetition_penalty: 1.05`
 | Model | Description |
 | --- | --- |
 | [**LFM2.5-8B-A1B**](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B) | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers, vLLM, and SGLang. |
 | [LFM2.5-8B-A1B-GGUF](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF) | Quantized format for llama.cpp and compatible tools. Optimized for edge inference and local deployment. |
 | [LFM2.5-8B-A1B-ONNX](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-ONNX) | ONNX Runtime format for cross-platform deployment. |
 | [LFM2.5-8B-A1B-MLX](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-MLX-8bit) | MLX format for Apple Silicon. Optimized for fast inference on Mac devices. |
 We recommend using LFM2.5-8B-A1B for agentic workflows, tool use, structured outputs, multilingual assistants, and on-device personal-assistant applications. It is not the best fit for heavy programming or knowledge-intensive question answering without retrieval.
 ### Chat Template
 LFM2.5 uses a ChatML-like format. See the [Chat Template documentation](https://docs.liquid.ai/lfm/key-concepts/chat-template) for details. Example:
 ```
 <|startoftext|><|im_start|>system
 You are a helpful assistant trained by Liquid AI.<|im_end|>
 <|im_start|>user
 What is C. elegans?<|im_end|>
 <|im_start|>assistant
 ```
 Because LFM2.5-8B-A1B is a reasoning model, assistant turns contain an explicit chain of thought before the final answer. You can use [`tokenizer.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_templating#using-applychattemplate) to format your messages automatically.
 ### Tool Use
 LFM2.5 supports function calling in four steps:
 1. **Function definition**: Provide the list of tools as a JSON object in the system prompt, or use [`tokenizer.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_extras#passing-tools) with `tools=...`.
 2. **Function call**: By default, LFM2.5 writes Pythonic function calls (a Python list between `<|tool_call_start|>` and `<|tool_call_end|>` special tokens), as the assistant answer. You can override this behavior by asking the model to output JSON function calls in the system prompt.
 3. **Function execution**: Execute the call and return the result with the `tool` role.
 4. **Final answer**: LFM2.5 interprets the tool output and returns a plain-text answer addressing the original prompt.
 See the [Tool Use documentation](https://docs.liquid.ai/lfm/key-concepts/tool-use) for the full guide. Example:
 ```
 <|startoftext|><|im_start|>system
 List of tools: [{"name": "get_candidate_status", "description": "Retrieves the current status of a candidate in the recruitment process", "parameters": {"type": "object", "properties": {"candidate_id": {"type": "string", "description": "Unique identifier for the candidate"}}, "required": ["candidate_id"]}}]<|im_end|>
 <|im_start|>user
 What is the current status of candidate ID 12345?<|im_end|>
 <|im_start|>assistant
 <|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
 <|im_start|>tool
 [{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}]<|im_end|>
 <|im_start|>assistant
 The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>
 ```
 ## 🏃 Inference
 LFM2.5-8B-A1B is supported by many inference frameworks. See the [Inference documentation](https://docs.liquid.ai/lfm/inference/transformers) for the full list.
 | Name | Description | Docs | Notebook |
 |------|-------------|------|:--------:|
 | [Transformers](https://github.com/huggingface/transformers) | Simple inference with direct access to model internals. | <a href="https://docs.liquid.ai/lfm/inference/transformers">Link</a> | <a href="https://colab.research.google.com/drive/1_q3jQ6LtyiuPzFZv7Vw8xSfPU5FwkKZY?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | [vLLM](https://github.com/vllm-project/vllm) | High-throughput production deployments with GPU. | <a href="https://docs.liquid.ai/lfm/inference/vllm">Link</a> | <a href="https://colab.research.google.com/drive/1VfyscuHP8A3we_YpnzuabYJzr5ju0Mit?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | [llama.cpp](https://github.com/ggml-org/llama.cpp) | Cross-platform inference with CPU offloading. | <a href="https://docs.liquid.ai/lfm/inference/llama-cpp">Link</a> | <a href="https://colab.research.google.com/drive/1ohLl3w47OQZA4ELo46i5E4Z6oGWBAyo8?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | [MLX](https://github.com/ml-explore/mlx) | Apple's machine learning framework optimized for Apple Silicon. | <a href="https://docs.liquid.ai/lfm/inference/mlx">Link</a> | — |
 | [LM Studio](https://lmstudio.ai/) | Desktop application for running LLMs locally. | <a href="https://docs.liquid.ai/lfm/inference/lm-studio">Link</a> | — |
 Quick start with Transformers (compatible with `transformers>=5.0.0`):
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
 model_id = "LiquidAI/LFM2.5-8B-A1B"
 model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    dtype="bfloat16",
 #   attn_implementation="flash_attention_2" <- uncomment on compatible GPU
 )
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
 prompt = "What is C. elegans?"
 input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": prompt}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
 ).to(model.device)
 output = model.generate(
    input_ids,
    do_sample=True,
    temperature=0.2,
    top_k=80,
    repetition_penalty=1.05,
    max_new_tokens=8192,
    streamer=streamer,
 )
 ```
 ## 🔧 Fine-Tuning
 We recommend fine-tuning LFM2.5 for your specific use case to achieve the best results.
 | Name | Description | Docs | Notebook |
 |------|-------------|------|----------|
 | CPT ([Unsloth](https://github.com/unslothai/unsloth)) | Continued Pre-Training using Unsloth for text completion. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/10fm7eNMezs-DSn36mF7vAsNYlOsx9YZO?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | CPT ([Unsloth](https://github.com/unslothai/unsloth)) | Continued Pre-Training using Unsloth for translation. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/1gaP8yTle2_v35Um8Gpu9239fqbU7UgY8?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | SFT ([Unsloth](https://github.com/unslothai/unsloth)) | Supervised Fine-Tuning with LoRA using Unsloth. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/1vGRg4ksRj__6OLvXkHhvji_Pamv801Ss?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | SFT ([TRL](https://github.com/huggingface/trl)) | Supervised Fine-Tuning with LoRA using TRL. | <a href="https://docs.liquid.ai/lfm/fine-tuning/trl">Link</a> | <a href="https://colab.research.google.com/drive/1j5Hk_SyBb2soUsuhU0eIEA9GwLNRnElF?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | DPO ([TRL](https://github.com/huggingface/trl)) | Direct Preference Optimization with LoRA using TRL. | <a href="https://docs.liquid.ai/lfm/fine-tuning/trl">Link</a> | <a href="https://colab.research.google.com/drive/1MQdsPxFHeZweGsNx4RH7Ia8lG8PiGE1t?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | GRPO ([Unsloth](https://github.com/unslothai/unsloth)) | GRPO with LoRA using Unsloth. | <a href="https://docs.liquid.ai/lfm/fine-tuning/unsloth">Link</a> | <a href="https://colab.research.google.com/drive/1mIikXFaGvcW4vXOZXLbVTxfBRw_XsXa5?usp=sharing"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 | GRPO ([TRL](https://github.com/huggingface/trl)) | GRPO with LoRA using TRL. | <a href="https://docs.liquid.ai/lfm/fine-tuning/trl">Link</a> | <a href="https://colab.research.google.com/github/Liquid4All/cookbook/blob/main/finetuning/notebooks/grpo_for_verifiable_tasks.ipynb"><img src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/vlOyMEjwHa_b_LXysEu2E.png" width="110" alt="Colab link"></a> |
 ## 📊 Performance
 ### Improvements over LFM2-8B-A1B
 Thanks to reasoning, scaled-up pre-training, and large-scale RL, LFM2.5-8B-A1B improves over its predecessor across the board:
 | Benchmark | LFM2-8B-A1B | LFM2.5-8B-A1B | Δ |
 | :--- | ---: | ---: | ---: |
 | AA-Omniscience Index | -78.42 | -24.70 | +53.62 |
 | AA-Omniscience Accuracy | 7.33 | 8.67 | +1.34 |
 | AA-Omniscience Non-Hallucination Rate | 7.46 | 63.47 | +56.01 |
 | IFEval | 79.44 | 91.84 | +12.40 |
 | IFBench | 26.00 | 56.47 | +30.47 |
 | Multi-IF | 58.54 | 79.93 | +21.39 |
 | MATH500 | 74.80 | 88.76 | +13.96 |
 | AIME25 | 20.00 | 42.53 | +22.53 |
 | BFCLv3 | 45.07 | 64.36 | +19.29 |
 | BFCLv4 | 25.52 | 48.50 | +22.98 |
 | Tau² Telecom | 13.60 | 88.07 | +74.47 |
 | Tau² Retail | 7.02 | 39.82 | +32.80 |
 ### Knowledge and instruction following
 | Model | Parameters | AA-Omni. Index | AA-Omni. Accuracy | AA-Omni. Non-Halluc. | IFEval | IFBench | Multi-IF |
 | :--- | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
 | LFM2.5-8B-A1B | 8B/A1B | -24.70 | 8.67 | 63.47 | 91.84 | 56.47 | 79.93 | |
 | Granite-4.0-H-Tiny | 7B/A1B | -75.50 | 9.37 | 6.38 | 82.23 | 21.28 | 59.00 | |
 | Qwen3.5-4B | 4B | -51.53 | 17.20 | 16.99 | 87.80 | 50.38 | 67.43 | |
 | Qwen3-30B-A3B-Thinking-2507 | 30.5B/3.3B | -51.31 | 18.80 | 13.87 | 90.82 | 51.11 | 79.04 | |
 | Gemma-4-E2B-IT | 5.1B | -72 | 7.00 | 15.05 | 82.93 | 33.53 | 69.70 | |
 | Gemma-4-E4B-IT | 8B | -50.67 | 8.10 | 36.06 | 87.74 | 39.48 | 77.58 | |
 | Gemma-4-26B-A4B-IT | 26B/4B | -62.07 | 14.37 | 10.75 | 91.40 | 47.25 | 82.06 | |
 | gpt-oss-20b | 21B/3.6B | -49.17 | 14.57 | 24.50 | 86.73 | 58.65 | 76.64 | |
 ### Math and agentic workflows
 | Model | Parameters | MATH500 | AIME25 | AIME26 | BFCLv3 | BFCLv4 | Tau² Telecom | Tau² Retail |
 |---|---|---|---|---|---|---|---|---|
 | LFM2.5-8B-A1B | 8B/A1B | 88.76 | 42.53 | 50.00 | 64.79 | 49.73 | 88.07 | 39.82 |
 | Granite-4.0-H-Tiny | 7B/A1B | 59.20 | 4.93 | 3.33 | 56.89 | 28.52 | 16.67 | 18.42 |
 | Qwen3.5-4B | 4B | 80.76 | 54.28 | 58.33 | 71.06 | 54.01 | 87.72 | 71.93 |
 | Qwen3-30B-A3B-Thinking-2507 | 30.5B/3.3B | 86.48 | 71.67 | 66.67 | 73.39 | 50.53 | 21.93 | 56.14 |
 | Gemma-4-E2B-IT | 5.1B | 64.00 | 26 | 30 | 56.44 | 31.91 | 22.37 | 18.95 |
 | Gemma-4-E4B-IT | 8B | 65.00 | 34.33 | 40.67 | 57.31 | 33.92 | 26.75 | 42.11 |
 ### CPU Inference
 ![image](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/yWAChLNCguGTl9lXBL47p.png)
 ### GPU Inference
 LFM2.5-8B-A1B is the fastest model in its size class, reaching **18.5K output tokens per second at high concurrency**, over 1.6B tokens per day on a single H100.
 ![image](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/LX3oIXQeDm51eaLQs64an.png)
 ## 📬 Contact
 - Got questions or want to connect? [Join our Discord community](https://discord.com/invite/liquid-ai).
 - If you are interested in custom solutions with edge deployment, please contact [our sales team](https://www.liquid.ai/contact).
 ## Citation
 ```bibtex
@article{liquidAI20268BA1B,
  author  = {Liquid AI},
  title   = {LFM2.5-8B-A1B: Personal Assistant On Your Laptop},
  journal = {Liquid AI Blog},
  year    = {2026},
  note    = {www.liquid.ai/blog/lfm2-5-8b-a1b},
 }
 ```
 ```bibtex
@article{liquidai2025lfm2,
  title   = {LFM2 Technical Report},
  author  = {Liquid AI},
  journal = {arXiv preprint arXiv:2511.23404},
  year    = {2025}
 }
 ```
--- a/imatrix_unsloth.gguf_file
+++ b/imatrix_unsloth.gguf_file
@@ -0,0 +1,3 @@
 version https://git-lfs.github.com/spec/v1
 oid sha256:09cf3e3f38c9906dc0239750f524d4e728b8fe985ad04bcfc07dd55bbb6e4474
 size 17375232