commit 5917fe27bd967f039af99bbc4df6fd40dbc268e8 Author: ModelHub XC Date: Mon Jul 20 15:05:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: unsloth/LFM2.5-1.2B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc6283e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,68 @@ +*.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 + +*.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 + +LFM2.5-1.2B-Thinking-BF16.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-UD-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +imatrix_unsloth.gguf_file filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-1.2B-Thinking-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/LFM2.5-1.2B-Thinking-BF16.gguf b/LFM2.5-1.2B-Thinking-BF16.gguf new file mode 100644 index 0000000..6c3b96e --- /dev/null +++ b/LFM2.5-1.2B-Thinking-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2ee9fade42a520afb058d3998e7625b96a6ca3ce5ac20ddea499a5ce092a06c +size 2343326944 diff --git a/LFM2.5-1.2B-Thinking-Q2_K.gguf b/LFM2.5-1.2B-Thinking-Q2_K.gguf new file mode 100644 index 0000000..d07a828 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739428486ef5ea661f7012e174f6f3a7d1fbec8ca19baa6b565aeb3658b2699d +size 483398880 diff --git a/LFM2.5-1.2B-Thinking-Q2_K_L.gguf b/LFM2.5-1.2B-Thinking-Q2_K_L.gguf new file mode 100644 index 0000000..d07a828 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739428486ef5ea661f7012e174f6f3a7d1fbec8ca19baa6b565aeb3658b2699d +size 483398880 diff --git a/LFM2.5-1.2B-Thinking-Q3_K_M.gguf b/LFM2.5-1.2B-Thinking-Q3_K_M.gguf new file mode 100644 index 0000000..e01a783 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f70d30ceab2805f2da29115999cc2d9b342ef56bc867878812263126061f627 +size 600347872 diff --git a/LFM2.5-1.2B-Thinking-Q3_K_S.gguf b/LFM2.5-1.2B-Thinking-Q3_K_S.gguf new file mode 100644 index 0000000..664ef35 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65478f974a9980c8cd6484f977a3a495d32e955976deaacd2113716c6e3e3cd +size 558159072 diff --git a/LFM2.5-1.2B-Thinking-Q4_0.gguf b/LFM2.5-1.2B-Thinking-Q4_0.gguf new file mode 100644 index 0000000..c3dc760 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7b6908532b3abb7ba9e67ee602f98e2737a43da9a0d25c21b3aefd70db920c +size 695751904 diff --git a/LFM2.5-1.2B-Thinking-Q4_1.gguf b/LFM2.5-1.2B-Thinking-Q4_1.gguf new file mode 100644 index 0000000..312b8e5 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c7315c9f3d2131fa486772b6cf40e14a99e4d6227edee1e4e9b9a86a98d0de +size 760501472 diff --git a/LFM2.5-1.2B-Thinking-Q4_K_M.gguf b/LFM2.5-1.2B-Thinking-Q4_K_M.gguf new file mode 100644 index 0000000..46ace81 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251867cddd9e1240ec0d8a733cf705629631fbe36c9170c54b968388fae3ba7e +size 730895584 diff --git a/LFM2.5-1.2B-Thinking-Q4_K_S.gguf b/LFM2.5-1.2B-Thinking-Q4_K_S.gguf new file mode 100644 index 0000000..1b970c5 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a002e6c04d87be2e660f4765fb2423660519373f328a3fc63b2dac61b92177d3 +size 700470496 diff --git a/LFM2.5-1.2B-Thinking-Q5_K_M.gguf b/LFM2.5-1.2B-Thinking-Q5_K_M.gguf new file mode 100644 index 0000000..86d96d7 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8308803c1b2f376d800548dc37159a58c181431a367766a8de772622cf87b1f9 +size 843355360 diff --git a/LFM2.5-1.2B-Thinking-Q5_K_S.gguf b/LFM2.5-1.2B-Thinking-Q5_K_S.gguf new file mode 100644 index 0000000..f41a4ca --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5b311c2c5b409427328d08693bffdd2d863bdcb2b47a72aea7acb510672184 +size 825251040 diff --git a/LFM2.5-1.2B-Thinking-Q6_K.gguf b/LFM2.5-1.2B-Thinking-Q6_K.gguf new file mode 100644 index 0000000..b16a3b8 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d05e9aa3dceb5f17a8daa0bc94bbbda852c406dcfd8a204c6c7a2a1fed59da +size 962843872 diff --git a/LFM2.5-1.2B-Thinking-Q8_0.gguf b/LFM2.5-1.2B-Thinking-Q8_0.gguf new file mode 100644 index 0000000..1c628ed --- /dev/null +++ b/LFM2.5-1.2B-Thinking-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e842afad2eebd724e714a867aaa9b48b3b71df26cd0eebf634b1b41dbb129516 +size 1246254304 diff --git a/LFM2.5-1.2B-Thinking-UD-Q2_K_XL.gguf b/LFM2.5-1.2B-Thinking-UD-Q2_K_XL.gguf new file mode 100644 index 0000000..d07a828 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-UD-Q2_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739428486ef5ea661f7012e174f6f3a7d1fbec8ca19baa6b565aeb3658b2699d +size 483398880 diff --git a/LFM2.5-1.2B-Thinking-UD-Q3_K_XL.gguf b/LFM2.5-1.2B-Thinking-UD-Q3_K_XL.gguf new file mode 100644 index 0000000..e01a783 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-UD-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f70d30ceab2805f2da29115999cc2d9b342ef56bc867878812263126061f627 +size 600347872 diff --git a/LFM2.5-1.2B-Thinking-UD-Q4_K_XL.gguf b/LFM2.5-1.2B-Thinking-UD-Q4_K_XL.gguf new file mode 100644 index 0000000..46ace81 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-UD-Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251867cddd9e1240ec0d8a733cf705629631fbe36c9170c54b968388fae3ba7e +size 730895584 diff --git a/LFM2.5-1.2B-Thinking-UD-Q5_K_XL.gguf b/LFM2.5-1.2B-Thinking-UD-Q5_K_XL.gguf new file mode 100644 index 0000000..86d96d7 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-UD-Q5_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8308803c1b2f376d800548dc37159a58c181431a367766a8de772622cf87b1f9 +size 843355360 diff --git a/LFM2.5-1.2B-Thinking-UD-Q6_K_XL.gguf b/LFM2.5-1.2B-Thinking-UD-Q6_K_XL.gguf new file mode 100644 index 0000000..0564121 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-UD-Q6_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ea6c37115b3efa67a3de4fa374376accf38896e7cf3a1787011c110adcde71 +size 995349728 diff --git a/LFM2.5-1.2B-Thinking-UD-Q8_K_XL.gguf b/LFM2.5-1.2B-Thinking-UD-Q8_K_XL.gguf new file mode 100644 index 0000000..cecd5b4 --- /dev/null +++ b/LFM2.5-1.2B-Thinking-UD-Q8_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc26e36e68dfd4a20f02022999c43b242167a25c4532c23cf6bb8f232143d93 +size 1372083424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eaa770a --- /dev/null +++ b/README.md @@ -0,0 +1,277 @@ +--- +library_name: transformers +license: other +license_name: lfm1.0 +license_link: LICENSE +language: +- en +- ar +- zh +- fr +- de +- ja +- ko +- es +pipeline_tag: text-generation +tags: +- liquid +- unsloth +- lfm2.5 +- edge +base_model: +- LiquidAI/LFM2.5-1.2B-Thinking +--- +> [!NOTE] +> Includes Unsloth **chat template fixes**!
For `llama.cpp`, use `--jinja` +> + +
+

+ Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. +

+
+ + + + + + + + + +
+
+ + +
+ Liquid AI +
+ Try LFM • + Documentation • + LEAP +
+
+ +# LFM2.5-1.2B-Thinking + +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. + +- **Best-in-class performance**: A 1.2B model rivaling much larger models, bringing high-quality AI to your pocket. +- **Fast edge inference**: 239 tok/s decode on AMD CPU, 82 tok/s on mobile NPU. Runs under 1GB of memory with day-one support for llama.cpp, MLX, and vLLM. +- **Scaled training**: Extended pre-training from 10T to 28T tokens and large-scale multi-stage reinforcement learning. + +![LFM2.5-1.2B - Benchmarks-Light](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/KfNudLXnOZxAhlLp_1QVo.png) + +Find more information about LFM2.5 in our [blog post](https://www.liquid.ai/blog/introducing-lfm2-5-the-next-generation-of-on-device-ai). + +## 🗒️ Model Details + +| Model | Parameters | Description | +|-------|------------|-------------| +| [LFM2.5-1.2B-Base](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base) | 1.2B | Pre-trained base model for fine-tuning | +| [LFM2.5-1.2B-Instruct](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) | 1.2B | General-purpose instruction-tuned model | +| [**LFM2.5-1.2B-Thinking**](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | 1.2B | General-purpose reasoning model | +| [LFM2.5-1.2B-JP](https://huggingface.co/LiquidAI/LFM2.5-1.2B-JP) | 1.2B | Japanese-optimized chat model | +| [LFM2.5-VL-1.6B](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B) | 1.6B | Vision-language model with fast inference | +| [LFM2.5-Audio-1.5B](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B) | 1.5B | Audio-language model for speech and text I/O | + +LFM2.5-1.2B-Thinking is a general-purpose text-only model with the following features: + +- **Number of parameters**: 1.17B +- **Number of layers**: 16 (10 double-gated LIV convolution blocks + 6 GQA blocks) +- **Training budget**: 28T tokens +- **Context length**: 32,768 tokens +- **Vocabulary size**: 65,536 +- **Languages**: English, Arabic, Chinese, French, German, Japanese, Korean, Spanish +- **Generation parameters**: + - `temperature: 0.05` + - `top_k: 50` + - `repetition_penalty: 1.05` + +| Model | Description | +|-------|-------------| +| [**LFM2.5-1.2B-Thinking**](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking) | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers and vLLM. | +| [LFM2.5-1.2B-Thinking-GGUF](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-GGUF) | Quantized format for llama.cpp and compatible tools. Optimized for CPU inference and local deployment with reduced memory usage. | +| [LFM2.5-1.2B-Thinking-ONNX](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-ONNX) | ONNX Runtime format for cross-platform deployment. Enables hardware-accelerated inference across diverse environments (cloud, edge, mobile). | +| [LFM2.5-1.2B-Thinking-MLX](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit) | MLX format for Apple Silicon. Optimized for fast inference on Mac devices using the MLX framework. | + +We recommend using it for agentic tasks, data extraction, and RAG. It is not recommended for knowledge-intensive tasks and programming. + +### 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 as follows: + +1. **Function definition**: We recommend providing the list of tools as a JSON object in the system prompt. You can also use the [`tokenizer.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_extras#passing-tools) function 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**: The function call is executed, and the result is returned as a "tool" role. +4. **Final answer**: LFM2 interprets the outcome of the function call to address the original user prompt in plain text. + +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. | Link | Colab link | +| [vLLM](https://github.com/vllm-project/vllm) | High-throughput production deployments with GPU. | Link | Colab link | +| [llama.cpp](https://github.com/ggml-org/llama.cpp) | Cross-platform inference with CPU offloading. | Link | Colab link | +| [MLX](https://github.com/ml-explore/mlx) | Apple's machine learning framework optimized for Apple Silicon. | Link | — | +| [LM Studio](https://lmstudio.ai/) | Desktop application for running LLMs locally. | Link | — | + +Here's a quick start example with Transformers: + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer + +model_id = "LiquidAI/LFM2.5-1.2B-Thinking" +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=0.1, + top_k=50, + top_p=0.1, + 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. | Link | Colab link | +| CPT ([Unsloth](https://github.com/unslothai/unsloth)) | Continued Pre-Training using Unsloth for translation. | Link | Colab link | +| SFT ([Unsloth](https://github.com/unslothai/unsloth)) | Supervised Fine-Tuning with LoRA using Unsloth. | Link | Colab link | +| SFT ([TRL](https://github.com/huggingface/trl)) | Supervised Fine-Tuning with LoRA using TRL. | Link | Colab link | +| DPO ([TRL](https://github.com/huggingface/trl)) | Direct Preference Optimization with LoRA using TRL. | Link | Colab link | +| GRPO ([Unsloth](https://github.com/unslothai/unsloth)) | GRPO with LoRA using Unsloth. | Link | Colab link | + +## 📊 Performance + +### Benchmarks + +We compared LFM2.5-1.2B-Thinking with relevant sub-2B models on a diverse suite of benchmarks. + +| Model | GPQA Diamond | MMLU-Pro | IFEval | IFBench | Multi-IF | GSM8K | MATH-500 | AIME25 | BFCLv3 | +| -------------------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | ----------------- | +| **LFM2.5-1.2B-Thinking** | 37.86
(± 0.83) | 49.65
(± 0.18) | 88.42
(± 0.35) | 44.85
(± 0.73) | 69.33
(± 0.09) | 85.60
(± 0.00) | 87.96
(± 0.72) | 31.73
(± 1.81) | 56.97
(± 0.30) | +| Qwen3-1.7B (thinking mode) | 36.93
(± 2.07) | 56.68
(± 1.29) | 71.65
(± 0.13) | 25.88
(± 0.30) | 60.33
(± 0.02) | 85.60
(± 1.13) | 81.92
(± 2.99) | 36.27
(± 1.24) | 55.41
(± 0.04) | +| LFM2.5-1.2B-Instruct | 38.89 | 44.35 | 86.23 | 47.33 | 60.98 | 64.52 | 63.20 | 14.00 | 49.12 | +| Qwen3-1.7B (instruct mode) | 34.85 | 42.91 | 73.68 | 21.33 | 56.48 | 33.66 | 70.40 | 9.33 | 46.30 | +| Granite-4.0-H-1B | 24.34 | 27.64 | 80.08 | 24.93 | 47.56 | 69.60 | 47.20 | 1 | 50.69 | +| Granite-4.0-1B | 24.24 | 33.53 | 79.61 | 21 | 43.65 | 73.42 | 44.80 | 3.33 | 52.43 | +| Gemma 3 1B IT | 24.24 | 14.04 | 63.25 | 20.47 | 44.31 | 42.15 | 45.20 | 1 | 16.64 | +| Llama 3.2 1B Instruct | 16.57 | 20.80 | 52.37 | 15.93 | 30.16 | 39.04 | 23.40 | 0.33 | 21.44 | + +GPQA, MMLU-Pro, IFBench, and AIME25 follow [ArtificialAnalysis's methodology](https://artificialanalysis.ai/methodology/intelligence-benchmarking). For IFEval and Multi-IF, we report the average score across strict and loose prompt and instruction accuracies. For BFCLv3, we report the final weighted average score with a custom Liquid handler to support our tool use template. + +Based on the same methodology, we report the average score and standard deviation across five runs with `temperature=0.6` for thinking models. For instruct models, we report scores using greedy decoding. + +### Response length + +In comparison with Qwen3-1.7B (thinking mode), it requires fewer output tokens while offering higher overall performance. + +![LFM2.5-1.2B - Average Response Length](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/Gcq_HUYLVC779xOuut2EI.png) + +### Inference speed + +LFM2.5-1.2B-Thinking offers extremely fast inference speed on CPUs with a low memory profile compared to similar-sized models. + +![LFM2.5-1.2B - Inference Performance](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/4ODY8nGws22vICfcMTxNx.png) + +In addition, we are partnering with AMD, Qualcomm, Nexa AI, and FastFlowLM to bring the LFM2.5 family to NPUs. These optimized models are available through our partners, enabling highly efficient on-device inference. + +We report the following numbers with 1K prefill and 100 decode tokens: + +| Device | Inference | Framework | Model | Prefill (tok/s) | Decode (tok/s) | Memory | +| ---------------------------------------------------- | --------- | ---------------- | -------------------- | --------------- | -------------- | ------ | +| AMD Ryzen AI 395+ | NPU | FastFlowLM | LFM2.5-1.2B-Thinking | 1487 | 60 | 1600MB (full context) | +| AMD Ryzen AI 9 HX 370 | NPU | FastFlowLM | LFM2.5-1.2B-Thinking | 1487 | 57 | 1600MB (full context) | +| AMD Ryzen AI 9 HX 370 | CPU | llama.cpp (Q4_0) | LFM2.5-1.2B-Thinking | 2975 | 116 | 856MB | +| Qualcomm Snapdragon® X Elite | NPU | NexaML | LFM2.5-1.2B-Thinking | 2591 | 63 | 0.9GB | +| Qualcomm Snapdragon® Gen4 (ROG Phone9 Pro) | NPU | NexaML | LFM2.5-1.2B-Thinking | 4391 | 82 | 0.9GB | +| Qualcomm Dragonwing IQ9 (IQ-9075) (IoT) | NPU | NexaML | LFM2.5-1.2B-Thinking | 2143 | 53 | 0.9 GB | +| Qualcomm Snapdragon® Gen4 (Samsung Galaxy S25 Ultra) | CPU | llama.cpp (Q4_0) | LFM2.5-1.2B-Thinking | 335 | 70 | 719MB | + +**LFM2.5-1.2B-Thinking excels at long-context inference.** For example, on AMD Ryzen™ NPUs with FastFlowLM, decoding throughput sustains ~52 tok/s at 16K context and ~46 tok/s even at the full 32K context, indicating robust long-context scalability. For more details on longer context benchmarks on AMD Ryzen™ NPUs with FastFlowLM, please review these [here](https://fastflowlm.com/docs/benchmarks/lfm2_results/). + +These capabilities unlock new deployment scenarios across various devices, including vehicles, mobile devices, laptops, IoT devices, and embedded systems. + +## Contact + +For enterprise solutions and edge deployment, contact [sales@liquid.ai](mailto:sales@liquid.ai). + +## Citation + +```bibtex +@article{liquidAI2026thinking, + author = {Liquid AI}, + title = {LFM2.5-1.2B-Thinking: On-Device Reasoning Under 1GB}, + journal = {Liquid AI Blog}, + year = {2026}, + note = {www.liquid.ai/blog/lfm2-5-1-2b-thinking-on-device-reasoning-under-1gb}, +} +``` + +```bibtex +@article{liquidai2025lfm2, + title={LFM2 Technical Report}, + author={Liquid AI}, + journal={arXiv preprint arXiv:2511.23404}, + year={2025} +} +``` \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/imatrix_unsloth.gguf_file b/imatrix_unsloth.gguf_file new file mode 100644 index 0000000..823b094 --- /dev/null +++ b/imatrix_unsloth.gguf_file @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8ccc948c333cf335f7208e0331e8aea34734b5f3045d949ba3c745e5916d29 +size 1161536