初始化项目，由ModelHub XC社区提供模型
Model: unsloth/LFM2.5-230M-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
69
.gitattributes
vendored
Normal file
69
.gitattributes
vendored
Normal file
@@ -0,0 +1,69 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
3
LFM2.5-230M-BF16.gguf
Normal file
3
LFM2.5-230M-BF16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:41fcd956ef68b160491e3391e409618f9120b51489669bbb0134d441037ea886
|
||||||
|
size 461884384
|
||||||
3
LFM2.5-230M-IQ4_NL.gguf
Normal file
3
LFM2.5-230M-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:55445c6005f0762eda63189977d57623126850b122e9084187b8559dfcc3d554
|
||||||
|
size 149081280
|
||||||
3
LFM2.5-230M-IQ4_XS.gguf
Normal file
3
LFM2.5-230M-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fa993c8160ca96dd4b777d18db164c20b681fdda0924cab16bc73ddf7ff91620
|
||||||
|
size 144002240
|
||||||
3
LFM2.5-230M-Q3_K_M.gguf
Normal file
3
LFM2.5-230M-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5e6fa272886660bb8ecbe10cf1bba3243cb628c2f52649d53be7461477e02071
|
||||||
|
size 133754048
|
||||||
3
LFM2.5-230M-Q3_K_S.gguf
Normal file
3
LFM2.5-230M-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:51926cdf373df765ba504b8b714852acc951b7bb3a1a272e62843e561063c406
|
||||||
|
size 127495360
|
||||||
3
LFM2.5-230M-Q4_0.gguf
Normal file
3
LFM2.5-230M-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7453be098ba096654200229288b7d17e457ed21c1e1c90d0bb8f53234ed69420
|
||||||
|
size 149245120
|
||||||
3
LFM2.5-230M-Q4_1.gguf
Normal file
3
LFM2.5-230M-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3aa08b5a649ec07e4332873d1cc0a8202a2f837951ff09eab47dc76e11ac3acb
|
||||||
|
size 159239360
|
||||||
3
LFM2.5-230M-Q4_K_M.gguf
Normal file
3
LFM2.5-230M-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:02e773bbba1c58f9f4fe98ae02bedbaa2a788d953d123de12021e5e205cc5041
|
||||||
|
size 153406656
|
||||||
3
LFM2.5-230M-Q4_K_S.gguf
Normal file
3
LFM2.5-230M-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2305793cd45b525091ecacc9c4802750d4a032de6d65f7917fc412107eae9496
|
||||||
|
size 149671104
|
||||||
3
LFM2.5-230M-Q5_K_M.gguf
Normal file
3
LFM2.5-230M-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b3cfb36e944abbd4520dcdb48dac7e041980c6ab890752bed6bb941fd2dc34a8
|
||||||
|
size 171625664
|
||||||
3
LFM2.5-230M-Q5_K_S.gguf
Normal file
3
LFM2.5-230M-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:70b602e42ae461200effe0fb072df30909d1457640d0886b67df5aa8199b8410
|
||||||
|
size 169397440
|
||||||
3
LFM2.5-230M-Q6_K.gguf
Normal file
3
LFM2.5-230M-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:246842725f0ad102eeb17dda1be65d6e5e62b4e7b787339b5173896c1c03b572
|
||||||
|
size 190983360
|
||||||
3
LFM2.5-230M-Q8_0.gguf
Normal file
3
LFM2.5-230M-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f69ac4ed06479bf45477389dbd2a4a3b4bc9bb232511cc060d39ff79d09ef75a
|
||||||
|
size 246598848
|
||||||
3
LFM2.5-230M-UD-IQ2_M.gguf
Normal file
3
LFM2.5-230M-UD-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6d13d58ca428f6427c219a748622a0bada74acfc729477aea3518f92480070af
|
||||||
|
size 105458880
|
||||||
3
LFM2.5-230M-UD-IQ3_XXS.gguf
Normal file
3
LFM2.5-230M-UD-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bccfb87f7c664f35db9fa6efcf328a6c7d98cae177b855136bdc55ceae8a3da1
|
||||||
|
size 112884928
|
||||||
3
LFM2.5-230M-UD-Q2_K_XL.gguf
Normal file
3
LFM2.5-230M-UD-Q2_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0cd46d69e74904ddef099fa360b76971495654b48339dbdd731f7fb329b1bfa6
|
||||||
|
size 119807168
|
||||||
3
LFM2.5-230M-UD-Q3_K_XL.gguf
Normal file
3
LFM2.5-230M-UD-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:303bdfd86a025177a213ec6e35453f2343159a86f0588f7c8f74d18a33417aef
|
||||||
|
size 139693248
|
||||||
3
LFM2.5-230M-UD-Q4_K_XL.gguf
Normal file
3
LFM2.5-230M-UD-Q4_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:97c51933508fdd42428d64444b9fcf983a69e6e0403d7d1f38976f5c347857a7
|
||||||
|
size 159988928
|
||||||
3
LFM2.5-230M-UD-Q5_K_XL.gguf
Normal file
3
LFM2.5-230M-UD-Q5_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e9043710ea68fef389c5720d8f6ff2240cd1699062bc38073efbaa4bf86939c2
|
||||||
|
size 172551360
|
||||||
3
LFM2.5-230M-UD-Q6_K_XL.gguf
Normal file
3
LFM2.5-230M-UD-Q6_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bb63d2d2cb9aa29284bba2ad4b133b61ec542cf5325ab07912a1f23f958fc3fd
|
||||||
|
size 222981312
|
||||||
3
LFM2.5-230M-UD-Q8_K_XL.gguf
Normal file
3
LFM2.5-230M-UD-Q8_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6412661b3cfabd0ab8fa04d1ee753b4da21426150418ed6c3a278ba0c8632d40
|
||||||
|
size 350801088
|
||||||
256
README.md
Normal file
256
README.md
Normal file
@@ -0,0 +1,256 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: other
|
||||||
|
license_name: lfm1.0
|
||||||
|
license_link: LICENSE
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- ar
|
||||||
|
- zh
|
||||||
|
- fr
|
||||||
|
- de
|
||||||
|
- ja
|
||||||
|
- ko
|
||||||
|
- es
|
||||||
|
- pt
|
||||||
|
- it
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
tags:
|
||||||
|
- liquid
|
||||||
|
- unsloth
|
||||||
|
- lfm2.5
|
||||||
|
- edge
|
||||||
|
base_model:
|
||||||
|
- LiquidAI/LFM2.5-230M
|
||||||
|
---
|
||||||
|
<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>
|
||||||
|
|
||||||
|
# LFM2.5-230M
|
||||||
|
|
||||||
|
LFM2.5 is a family of hybrid models designed for **on-device deployment**. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.
|
||||||
|
|
||||||
|
- **Our most compact model yet**: 230M parameters that punch above their weight, bringing real capability to the tightest memory and compute budgets.
|
||||||
|
- **Fast edge inference**: Best throughput from low-cost CPUs to production GPUs, running at 213 tok/s decode speed on Galaxy S25 Ultra and 42 tok/s on a Raspberry Pi 5.
|
||||||
|
- **Built for agentic tasks**: Distilled from LFM2.5-350M and refined with multi-stage reinforcement learning, making it well-suited for tool use and data extraction.
|
||||||
|
|
||||||
|
Find more information about LFM2.5-230M in our [blog post](https://www.liquid.ai/blog/lfm2-5-230m).
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## 🗒️ Model Details
|
||||||
|
|
||||||
|
| Model | Parameters | Description |
|
||||||
|
|-------|------------|-------------|
|
||||||
|
| [LFM2.5-230M-Base](https://huggingface.co/LiquidAI/LFM2.5-230M-Base) | 230M | Pre-trained base model for fine-tuning |
|
||||||
|
| [**LFM2.5-230M**](https://huggingface.co/LiquidAI/LFM2.5-230M) | 230M | General-purpose instruction-tuned model |
|
||||||
|
|
||||||
|
LFM2.5-230M is a general-purpose text-only model with the following features:
|
||||||
|
|
||||||
|
- **Number of parameters**: 230M
|
||||||
|
- **Number of layers**: 14 (8 double-gated LIV convolution blocks + 6 GQA blocks)
|
||||||
|
- **Training budget**: 19T tokens
|
||||||
|
- **Context length**: 32,768 tokens
|
||||||
|
- **Vocabulary size**: 65,536
|
||||||
|
- **Knowledge cutoff**: Mid-2024
|
||||||
|
- **Languages**: English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish
|
||||||
|
- **Generation parameters**:
|
||||||
|
- `temperature: 0.1`
|
||||||
|
- `top_k: 50`
|
||||||
|
- `repetition_penalty: 1.05`
|
||||||
|
|
||||||
|
| Model | Description |
|
||||||
|
|-------|-------------|
|
||||||
|
| [**LFM2.5-230M**](https://huggingface.co/LiquidAI/LFM2.5-230M) | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers, vLLM, and SGLang. |
|
||||||
|
| [LFM2.5-230M-GGUF](https://huggingface.co/LiquidAI/LFM2.5-230M-GGUF) | Quantized format for llama.cpp and compatible tools. Optimized for edge inference and local deployment. |
|
||||||
|
| [LFM2.5-230M-ONNX](https://huggingface.co/LiquidAI/LFM2.5-230M-ONNX) | ONNX Runtime format for cross-platform deployment. |
|
||||||
|
| [LFM2.5-230M-MLX](https://huggingface.co/LiquidAI/LFM2.5-230M-MLX-8bit) | MLX format for Apple Silicon. Optimized for fast inference on Mac devices. |
|
||||||
|
|
||||||
|
We recommend using it for data extraction and lightweight on-device agentic pipelines. It is not recommended for reasoning-heavy workloads such as advanced math, code generation, or creative writing.
|
||||||
|
|
||||||
|
### 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
|
||||||
|
```
|
||||||
|
|
||||||
|
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 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> | — |
|
||||||
|
| [SGLang](https://github.com/vllm-project/vllm) | High-throughput production deployments with GPU. | <a href="https://docs.liquid.ai/deployment/gpu-inference/sglang">Link</a> | - </a> |
|
||||||
|
|
||||||
|
|
||||||
|
Quick start with Transformers (compatible with `transformers>=5.0.0`):
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
||||||
|
|
||||||
|
model_id = "LiquidAI/LFM2.5-230M"
|
||||||
|
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,
|
||||||
|
)["input_ids"].to(model.device)
|
||||||
|
|
||||||
|
output = model.generate(
|
||||||
|
input_ids,
|
||||||
|
do_sample=True,
|
||||||
|
temperature=0.1,
|
||||||
|
top_k=50,
|
||||||
|
repetition_penalty=1.05,
|
||||||
|
max_new_tokens=512,
|
||||||
|
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
|
||||||
|
|
||||||
|
### Benchmarks
|
||||||
|
|
||||||
|
| Model | GPQA Diamond | MMLU-Pro | IFEval | IFBench | Multi-IF |
|
||||||
|
|---|---|---|---|---|---|
|
||||||
|
| **LFM2.5-230M** | 25.41 | 20.25 | 71.71 | 38.40 | 37.70 |
|
||||||
|
| LFM2.5-350M | 30.64 | 20.01 | 76.96 | 40.69 | 44.92 |
|
||||||
|
| LFM2-350M | 27.58 | 19.29 | 64.96 | 18.20 | 32.92 |
|
||||||
|
| Granite 4.0-H-350M | 22.32 | 13.14 | 61.27 | 17.22 | 28.70 |
|
||||||
|
| Granite 4.0-350M | 25.91 | 12.84 | 53.48 | 15.98 | 24.21 |
|
||||||
|
| Qwen3.5-0.8B (Instruct) | 27.41 | 37.42 | 59.94 | 22.87 | 41.68 |
|
||||||
|
| Gemma 3 1B IT | 23.89 | 14.04 | 63.49 | 20.33 | 44.25 |
|
||||||
|
|
||||||
|
| Model | CaseReportBench | BFCLv3 | BFCLv4 | τ²-Bench Telecom | τ²-Bench Retail |
|
||||||
|
|---|---|---|---|---|---|
|
||||||
|
| **LFM2.5-230M** | 22.51 | 43.26 | 21.03 | 5.26 | 13.68 |
|
||||||
|
| LFM2.5-350M | 32.45 | 44.11 | 21.86 | 18.86 | 17.84 |
|
||||||
|
| LFM2-350M | 11.67 | 22.95 | 12.29 | 10.82 | 5.56 |
|
||||||
|
| Granite 4.0-H-350M | 12.44 | 43.07 | 13.28 | 13.74 | 6.14 |
|
||||||
|
| Granite 4.0-350M | 0.84 | 39.58 | 13.73 | 2.92 | 6.14 |
|
||||||
|
| Qwen3.5-0.8B (Instruct) | 13.83 | 35.08 | 18.70 | 12.57 | 6.14 |
|
||||||
|
| Gemma 3 1B IT | 2.28 | 16.61 | 7.17 | 9.36 | 6.43 |
|
||||||
|
|
||||||
|
### CPU Inference
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### GPU Inference
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
## 📬 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{liquidAI2026230M,
|
||||||
|
author = {Liquid AI},
|
||||||
|
title = {LFM2.5-230M: Built to Run Anywhere},
|
||||||
|
journal = {Liquid AI Blog},
|
||||||
|
year = {2026},
|
||||||
|
note = {www.liquid.ai/blog/lfm2-5-230m},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```bibtex
|
||||||
|
@article{liquidai2025lfm2,
|
||||||
|
title={LFM2 Technical Report},
|
||||||
|
author={Liquid AI},
|
||||||
|
journal={arXiv preprint arXiv:2511.23404},
|
||||||
|
year={2025}
|
||||||
|
}
|
||||||
|
```
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
3
imatrix_unsloth.gguf_file
Normal file
3
imatrix_unsloth.gguf_file
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b300198006edafb69098a1f28c00d5bcbb61fba9fdee6c14e358b0a2b1051ee2
|
||||||
|
size 434912
|
||||||
Reference in New Issue
Block a user