初始化项目，由ModelHub XC社区提供模型

Model: HattoriHanzo1/Liquid-LFM2-8B-Polish-Warrior
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+Liquid-LFM2-8B-Polish-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Liquid-LFM2-8B-Polish-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Liquid-LFM2-8B-Polish-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Liquid-LFM2-8B-Polish-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9068dde8a3a19f54263a9287ce495cef84ae5a16dc6500ebc14d26a7ff6f9674
+size 16685562240

Liquid-LFM2-8B-Polish-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d0c286ab51318691e8ba8920b446791b93455a4df9982aba9108c3e66cadae
+size 5044779392

Liquid-LFM2-8B-Polish-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd485edd069495b1b2bba656bcf8228386fe679ee461b7b51c84e846d756cac
+size 6849001856

README.md

@@ -0,0 +1,68 @@
+---
+language:
+- pl
+- en
+license: apache-2.0
+base_model: LiquidAI/LFM2-8B-A1B
+library_name: transformers
+tags:
+- liquid
+- lfm
+- polish
+- technical
+- electronics
+- programming
+- gguf
+- warrior-of-silicon
+- hattori-hanzo
+- moe
+- quantized
+metrics:
+- loss
+---
+
+# ⚔️ Liquid-LFM2-8B-Polish-Warrior (Hattori Hanzo Edition)
+
+### 📥 Szybkie Pobieranie (GGUF)
+Wersje zoptymalizowane do działania na domowym sprzęcie (Llama.cpp, LM Studio, Ollama):
+
+| Model | Rozmiar | Opis | Link |
+| :--- | :--- | :--- | :--- |
+| **Q6_K** | ~6.7 GB | Najwyższa jakość, minimalna strata precyzji | [Pobierz Q6](https://huggingface.co/Michal1981/Liquid-LFM2-8B-Polish-Warrior/resolve/main/Liquid-LFM2-8B-Polish-Q6_K.gguf?download=true) |
+| **Q4_K_M** | ~4.8 GB | Najlepszy balans szybkości i inteligencji | [Pobierz Q4](https://huggingface.co/Michal1981/Liquid-LFM2-8B-Polish-Warrior/resolve/main/Liquid-LFM2-8B-Polish-Q4_K_M.gguf?download=true) |
+| **BF16** | ~15.5 GB | Pełna precyzja (do dalszego treningu) | [Pobierz F16](https://huggingface.co/Michal1981/Liquid-LFM2-8B-Polish-Warrior/resolve/main/Liquid-LFM2-8B-Polish-F16.gguf?download=true) |
+
+---
+
+> [!IMPORTANT]
+> **[English Version]** | **[Polska Wersja Poniżej]**
+
+## 🇺🇸 English Description
+**Liquid-LFM2-8B-Polish-Warrior** is the first specialized Polish adaptation of the innovative **Liquid LFM2 8B (A1B)** architecture. This model was meticulously fine-tuned by **Michal1981 (Warrior of Silicon)** to excel in Polish language understanding, with a strong focus on technical contexts, electronics, and programming (specifically C# and Arduino/EMS).
+
+### 📊 Training Progress (Final Results)
+The model reached its peak performance (**Sweet Spot**) at step **2800**, demonstrating an ideal balance between knowledge retention and linguistic flexibility.
+
+| Step | Training Loss | Validation Loss | Status |
+| :--- | :--- | :--- | :--- |
+| 200 | 1.4674 | 1.4427 | Initialization |
+| 1400 | 1.2975 | 1.3431 | Breakthrough |
+| **2800** | **0.9594** | **1.3356** | 👑 **Sweet Spot** |
+
+---
+
+## 🇵🇱 Polska Wersja
+**Liquid-LFM2-8B-Polish-Warrior** to pierwsza polska adaptacja architektury **Liquid LFM2 8B (A1B)**. Model został wytrenowany przez **Michala1981 (Wojownika Krzemu)**, aby zapewnić najwyższą jakość obsługi języka polskiego, ze szczególnym uwzględnieniem żargonu technicznego, elektroniki oraz programowania (C#, Arduino, EMS).
+
+### ⚔️ Filozofia Projektu
+Model powstał w duchu "Hattori Hanzo" – kucia cyfrowych ostrzy zdolnych stawić czoła bogom. W moim języku nie istnieje słowo "nie da się". Jest tylko "trudniej wykonalne i zajmie więcej czasu".
+
+### 📈 Charakterystyka Treningu
+Najlepszą formę model osiągnął w kroku **2800**, wykazując się doskonałym zrozumieniem polskiej fleksji przy najniższym błędzie walidacji (**1.3356**).
+
+---
+
+## 👨‍💻 Creator & Credits
+* **User/Creator**: Michal1981 (Hattori Hanzo)
+* **Architecture**: Liquid AI (LFM2-8B-A1B)
+* **Motto**: *Qapla'! Success is a journey, not a destination.*

chat_template.jinja

@@ -0,0 +1,7 @@
+{{- bos_token -}}{%- set system_prompt = "" -%}{%- set ns = namespace(system_prompt="") -%}{%- if messages[0]["role"] == "system" -%} {%- set ns.system_prompt = messages[0]["content"] -%} {%- set messages = messages[1:] -%}{%- endif -%}{%- if tools -%} {%- set ns.system_prompt = ns.system_prompt + ("
+" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%} {%- for tool in tools -%} {%- if tool is not string -%} {%- set tool = tool | tojson -%} {%- endif -%} {%- set ns.system_prompt = ns.system_prompt + tool -%} {%- if not loop.last -%} {%- set ns.system_prompt = ns.system_prompt + ", " -%} {%- endif -%} {%- endfor -%} {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}{%- endif -%}{%- if ns.system_prompt -%} {{- "<|im_start|>system
+" + ns.system_prompt + "<|im_end|>
+" -}}{%- endif -%}{%- for message in messages -%} {{- "<|im_start|>" + message["role"] + "
+" -}} {%- set content = message["content"] -%} {%- if content is not string -%} {%- set content = content | tojson -%} {%- endif -%} {%- if message["role"] == "tool" -%} {%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%} {%- endif -%} {{- content + "<|im_end|>
+" -}}{%- endfor -%}{%- if add_generation_prompt -%} {{- "<|im_start|>assistant
+" -}}{%- endif -%}

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "Lfm2MoeForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "dtype": "bfloat16",
+  "eos_token_id": 7,
+  "hidden_size": 2048,
+  "intermediate_size": 7168,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2_moe",
+  "moe_intermediate_size": 1792,
+  "norm_eps": 1e-05,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_dense_layers": 2,
+  "num_experts": 32,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_theta": 1000000.0,
+  "routed_scaling_factor": 1.0,
+  "transformers_version": "4.57.0.dev0",
+  "use_cache": true,
+  "use_expert_bias": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "pad_token_id": 0,
+  "transformers_version": "4.57.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2702bbffccd758e246e358107adfd80b249c3c053abe0e56f305e4963227b8bc
+size 4994470712

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f447e91b7719b09b8c759b2e7b7b9a80ecf7190c5a57d93224c617a019f7945
+size 4999536568

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9378266fe56a38cefb983981d1f4da1d83b979fca8f30da61ddc0c05d0e20e45
+size 4996542840

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41501a0c7dd525bbab715a0656f959c3c134b9bec606633a3144176d274da327
+size 1689601384

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}