初始化项目，由ModelHub XC社区提供模型

Model: ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,44 @@
+*.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.Q8_0.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.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text

LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c8e2c49ce5287529babf80c3a6567fcf3f606ab166b0485c59f3aa5e4e17c5f
+size 483396768

LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c855d8378c5bd59818446b146ea17133af31335cd11d505b16dc0d9ce2fae3
+size 600345760

LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172d49168e77cdda0d43ba14658537afda16dc7699e93756def3ff18b0f769b4
+size 730893472

LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ce8b3d3b5c0f74bf2a517336572b11f242d3691c3ad479b1c2f1a3b5d5d25a
+size 843353248

LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfe31a7394ff6a5513bbbafff6171a700a9d20e3e6ec1854b7b49ce5c8e32d5
+size 962841760

LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def44364dbee1fba76deeefecb525f9d988ec37430a8ecf876096da6b1471cf2
+size 1246252192

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c22dc465cdd2c6fefd917ff4b90827ac30f9fd9c946bb5c09c31d742f335fb5
+size 730893472

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46473d1abe107a0061330ecc01e6abe998723303c2752098e91c900783209a47
+size 843353248

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e9da3d0d35a3dda79cc56995d637b289ec8d1c28a53e5505447f2a72d1ea2e
+size 1246252192

README.md

@@ -0,0 +1,105 @@
+---
+base_model: ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth
+tags:
+- gguf
+- llama.cpp
+- unsloth
+- lfm2
+- function-calling
+- quantized
+license: apache-2.0
+language:
+- en
+datasets:
+- Salesforce/xlam-function-calling-60k
+pipeline_tag: text-generation
+---
+
+# LFM2.5-1.2B-xLAM-Unsloth — GGUF quantized
+
+GGUF quantizations of [`ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth`](https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth),
+produced via [Unsloth](https://github.com/unslothai/unsloth) + llama.cpp's conversion scripts.
+
+| Field | Value |
+|---|---|
+| **Source checkpoint** | [`ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth`](https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth) |
+| **Base model** | [`LiquidAI/LFM2.5-1.2B-Instruct`](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) |
+| **Dataset** | [`Salesforce/xlam-function-calling-60k`](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) |
+| **Training** | N=1 full epoch (7,500 steps, effective batch=8) |
+| **Conversion** | Unsloth `save_pretrained_gguf` → llama.cpp GGUF |
+| **Quantization tool** | llama.cpp `llama-quantize` |
+
+## Available quantizations
+
+| File | Size | Notes |
+|---|---|---|
+| `LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q2_K.gguf` | smallest | 2-bit; extreme compression, quality loss |
+| `LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q3_K_M.gguf` | small | 3-bit; modest quality trade-off |
+| `LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q4_K_M.gguf` | recommended | 4-bit; best size/quality balance |
+| `LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q5_K_M.gguf` | balanced | 5-bit; near-full quality |
+| `LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q6_K.gguf` | high quality | 6-bit; minimal degradation |
+| `LFM2.5-1.2B-Function-Calling-xLAM-Unsloth.Q8_0.gguf` | largest | 8-bit; closest to bf16 source |
+
+**Recommended default:** `Q4_K_M` (4-bit, K-quant medium). For memory-constrained deployment, try `Q2_K` or `Q3_K_M`. For maximum fidelity, use `Q8_0`.
+
+## Usage
+
+### llama.cpp
+
+```bash
+# Text-only
+llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF --jinja -p "Find flights from SFO to NYC on December 25th" -n 256
+
+# Interactive chat
+llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF --jinja -cnv
+```
+
+### Ollama
+
+```bash
+ollama run hf.co/ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF:Q4_K_M
+```
+
+### llama-cpp-python
+
+```python
+from llama_cpp import Llama
+llm = Llama.from_pretrained(
+    repo_id="ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF",
+    filename="*Q4_K_M.gguf",
+    n_ctx=2048,
+)
+out = llm.create_chat_completion(
+    messages=[{"role": "user", "content": "Find flights from SFO to NYC on December 25th"}],
+    max_tokens=256,
+)
+print(out["choices"][0]["message"]["content"])
+```
+
+## Intended use
+
+For research and non-commercial experimentation only. Outputs should be independently verified before any downstream use.
+
+## Limitations
+
+- GGUF quantizations have unavoidable quality loss relative to the source bfloat16 checkpoint. Use `Q5_K_M` or `Q8_0` for best fidelity.
+- Inherits all limitations of the source merged checkpoint ([`ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth`](https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth)).
+- Limited to the 60 function schemas covered in the training dataset; performance on novel APIs may degrade.
+
+## Citation
+
+```bibtex
+@misc{ lfm25_12b_xlam_unsloth_2026_gguf ,
+  author = {Ermia Azarkhalili},
+  title = { LFM2.5-1.2B-xLAM-Unsloth — GGUF quantized },
+  year = {2026},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth-GGUF}}
+}
+```
+
+---
+
+This lfm2 model was trained 2× faster with [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 2048,
+  "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,
+  "dtype": "bfloat16",
+  "eos_token_id": 7,
+  "full_attn_idxs": null,
+  "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": "ermiaazarkhalili/LFM2.5-1.2B-Function-Calling-xLAM-Unsloth",
+  "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_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "unsloth_version": "2026.4.6",
+  "use_cache": false,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}