初始化项目，由ModelHub XC社区提供模型

Model: nphearum/Opus4.8-tuned-super-fast-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,43 @@
+*.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
+LFM2.5-1.2B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct.Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

LFM2.5-1.2B-Instruct.BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e9408ff2b4133cfd46c2115715f4406689078497279a2dab7987153906e12d
+size 2343326272

LFM2.5-1.2B-Instruct.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0e368661e07cc32266de8357bcb7e3f64e0d66582cebcfee25e01453e86867
+size 2343326272

LFM2.5-1.2B-Instruct.Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526aa4099f6c08416cb2bdd18e88e274071e6c144d3234981b7c561aa465a4f5
+size 515904064

LFM2.5-1.2B-Instruct.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f16c6b312dc356c143800c5ece38a5183d4e4c3d1f8854185f65d1b3b5d45f7
+size 600347200

LFM2.5-1.2B-Instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef34a320b9d3f7a09e28888f112b1a1362da027c87cb5d7e131bb0271754df39
+size 730894912

LFM2.5-1.2B-Instruct.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0665da4a49527fdfb1b9ba17d8f9cf519daffb1270b417a928e788ae19329c5
+size 843354688

LFM2.5-1.2B-Instruct.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6180dac36f986c0810ac61c8a118320edd83190b20b6346c682b227bcb6f85e2
+size 962843200

LFM2.5-1.2B-Instruct.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fde7b6a9c59c1cd3c3435cbff0ef8961b1d668f7e1e4aef064f7eb1d87b4856
+size 1246253632

README.md

@@ -0,0 +1,15 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+
+---
+
+# Opus4.8-tuned-super-fast-GGUF : GGUF
+
+This model was finetuned and converted to GGUF format
+
+**Example usage**:
+- For text only LLMs:    `llama-cli -hf nphearum/Opus4.8-tuned-super-fast-GGUF --jinja`
+- For multimodal models: `llama-mtmd-cli -hf nphearum/Opus4.8-tuned-super-fast-GGUF --jinja`

config.json

@@ -0,0 +1,59 @@
+{
+    "architectures": [
+        "Lfm2ForCausalLM"
+    ],
+    "block_auto_adjust_ff_dim": true,
+    "block_dim": 2048,
+    "block_ff_dim": 12288,
+    "block_ffn_dim_multiplier": 1.0,
+    "block_mlp_init_scale": 1.0,
+    "block_multiple_of": 256,
+    "block_norm_eps": 1e-05,
+    "block_out_init_scale": 1.0,
+    "block_use_swiglu": true,
+    "block_use_xavier_init": true,
+    "bos_token_id": 1,
+    "conv_L_cache": 3,
+    "conv_bias": false,
+    "conv_dim": 2048,
+    "conv_use_xavier_init": true,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 7,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "layer_types": [
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv",
+        "full_attention",
+        "conv"
+    ],
+    "max_position_embeddings": 128000,
+    "model_name": "unsloth/LFM2.5-1.2B-Instruct",
+    "model_type": "lfm2",
+    "norm_eps": 1e-05,
+    "num_attention_heads": 32,
+    "num_heads": 32,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rope_theta": 1000000.0,
+    "tie_embedding": true,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.6.9",
+    "use_cache": false,
+    "use_pos_enc": true,
+    "vocab_size": 65536
+}