commit 90dc803a698fc955800efb6670e802662649a13c Author: ModelHub XC Date: Wed Sep 23 18:27:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Xenobd/LFM-Improved Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a2d95ea --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.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 +LFM2.5-230M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-230M.Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-230M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-230M.F16.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-230M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-230M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-230M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-230M.F16.gguf b/LFM2.5-230M.F16.gguf new file mode 100644 index 0000000..3cb2deb --- /dev/null +++ b/LFM2.5-230M.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ad2bcea78345d4bcc022add2dff726793a2b2b741d8c51a270aa80cce1dd5e +size 461883776 diff --git a/LFM2.5-230M.Q2_K_L.gguf b/LFM2.5-230M.Q2_K_L.gguf new file mode 100644 index 0000000..7b8340f --- /dev/null +++ b/LFM2.5-230M.Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78003d1b3913cffb87f6dc3fc5751031d297a866535e3833e2577d56935092f +size 131926400 diff --git a/LFM2.5-230M.Q3_K_M.gguf b/LFM2.5-230M.Q3_K_M.gguf new file mode 100644 index 0000000..2097d11 --- /dev/null +++ b/LFM2.5-230M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b2feca1422a4f33ad22e407a3a911e4e8d8acd3668ec5329d797ff2eb63f41 +size 133753216 diff --git a/LFM2.5-230M.Q4_K_M.gguf b/LFM2.5-230M.Q4_K_M.gguf new file mode 100644 index 0000000..3b652a0 --- /dev/null +++ b/LFM2.5-230M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa04bdc88f24494e4dec7a71cbcc25c9d0f709eeda2a7e04b64fe600016fdf91 +size 153405824 diff --git a/LFM2.5-230M.Q5_K_M.gguf b/LFM2.5-230M.Q5_K_M.gguf new file mode 100644 index 0000000..64f2221 --- /dev/null +++ b/LFM2.5-230M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc56f16f96b7240cdd9f48bd1df50ec614710ad9e564c94636b09dfbc483b740 +size 171624832 diff --git a/LFM2.5-230M.Q6_K.gguf b/LFM2.5-230M.Q6_K.gguf new file mode 100644 index 0000000..7e29870 --- /dev/null +++ b/LFM2.5-230M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80c4f511848c4dabc10ce3519271710eb38f96d3963ff6b47cc598bb846233a +size 190982528 diff --git a/LFM2.5-230M.Q8_0.gguf b/LFM2.5-230M.Q8_0.gguf new file mode 100644 index 0000000..8b53f59 --- /dev/null +++ b/LFM2.5-230M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e0584cbf7802e7b9ade5ca4ed23df94de03d8b8f94c2b98e797c952bc605ee +size 246598016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a4045de --- /dev/null +++ b/README.md @@ -0,0 +1,20 @@ +--- +tags: +- gguf +- llama.cpp +- unsloth + +--- + +# LFM-Improved : GGUF + +This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth). + +**Example usage**: +- For text only LLMs: `llama-cli -hf Xenobd/LFM-Improved --jinja` +- For multimodal models: `llama-mtmd-cli -hf Xenobd/LFM-Improved --jinja` + +## Available Model files: +- `LFM2.5-230M.Q5_K_M.gguf` +This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) +[](https://github.com/unslothai/unsloth) diff --git a/config.json b/config.json new file mode 100644 index 0000000..0f07112 --- /dev/null +++ b/config.json @@ -0,0 +1,67 @@ +{ + "architectures": [ + "Lfm2ForCausalLM" + ], + "block__name_mlp": "parallel_mlp_merged", + "block_auto_adjust_ff_dim": false, + "block_dim": 1024, + "block_ffn_dim_multiplier": 1.0, + "block_ffn_te_autocast": false, + "block_ffn_use_quantized_params": false, + "block_mlp_init_scale": 1.0, + "block_multiple_of": 256, + "block_norm_eps": 1e-05, + "block_out_init_scale": 1.0, + "block_sequence_parallel_norm_across_tp": false, + "block_use_swiglu": true, + "block_use_xavier_init": true, + "bos_token_id": 1, + "conv_L_cache": 3, + "conv_bias": false, + "conv_dim": 1024, + "conv_use_xavier_init": true, + "dtype": "float16", + "eos_token_id": 7, + "ffn_te_autocast": false, + "ffn_use_quantized_params": false, + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 2560, + "layer_types": [ + "conv", + "conv", + "full_attention", + "conv", + "full_attention", + "conv", + "full_attention", + "conv", + "full_attention", + "conv", + "full_attention", + "conv", + "full_attention", + "conv" + ], + "max_position_embeddings": 128000, + "model_name": "unsloth/LFM2.5-230M", + "model_type": "lfm2", + "norm_eps": 1e-05, + "num_attention_heads": 16, + "num_heads": 16, + "num_hidden_layers": 14, + "num_key_value_heads": 8, + "pad_token_id": 0, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sequence_parallel_norm_across_tp": false, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "unsloth_fixed": true, + "unsloth_version": "2026.6.9", + "use_cache": false, + "use_pos_enc": true, + "vocab_size": 65536 +}