Initial GGUF upload

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* 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
+MetalGPT-1-32B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MetalGPT-1-32B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MetalGPT-1-32B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+MetalGPT-1-32B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

MetalGPT-1-32B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a78e9906144ee95796ad41bde86718f7a2f5e18f25bb964d104bd2ecd1f47de2
+size 19761766592

MetalGPT-1-32B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6690989f8872601f7567e0fcec874db1c16175932bc4768c934bfd97d9e3d9
+size 18770862272

MetalGPT-1-32B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f489067eb0dffaef88646cfab7ee9330dfaaa5c1ca72fdff21d057548f5884
+size 26882597696

MetalGPT-1-32B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9fdb60bd3735f238ba99d385d203d983abdfdcc60ec38c56832cb000615a595
+size 34816397888

README.md

@@ -0,0 +1,109 @@
+---
+base_model: nn-tech/MetalGPT-1
+model_type: qwen
+tags:
+  - mining
+  - metallurgy
+  - gguf
+  - text-generation
+license: apache-2.0
+language:
+  - ru
+pipeline_tag: text-generation
+---
+
+# MetalGPT-1 GGUF
+
+This repository contains **unofficial GGUF conversions** of the [`nn-tech/MetalGPT-1`](https://huggingface.co/nn-tech/MetalGPT-1) model for use with GGUF-compatible runtimes.
+
+MetalGPT-1 is a 32B chat model based on **Qwen/Qwen3-32B**, further trained with both continual pre-training and supervised fine-tuning on domain-specific data from the mining and metallurgy industry.
+
+> ⚠️ Disclaimer:  
+> This repository is **not** affiliated with the original authors of MetalGPT-1.  
+> These are pure quantizations of the original model weights - no additional training, fine-tuning, or modifications were applied.  
+> Quality, correctness, and safety of the quantized variants are not guaranteed.
+
+See the original model card: https://huggingface.co/nn-tech/MetalGPT-1
+
+---
+
+## GGUF variants in this repository
+
+The following GGUF quantized variants of MetalGPT-1 are provided:
+
+| File name                  | Quantization | Size (GB) | Notes                                                          |
+| :------------------------- | :----------- | :-------- | :------------------------------------------------------------- |
+| `MetalGPT-1-32B-Q8_0.gguf`   | Q8_0         | 32.43     | Near‑F16 quality, high VRAM                                    |
+| `MetalGPT-1-32B-Q6_K.gguf`   | Q6_K         | 25.04     | Higher quality, more VRAM                                      |
+| `MetalGPT-1-32B-Q4_K_M.gguf` | Q4_K_M       | 18.40     | Good quality, very memory‑efficient                            |
+| `MetalGPT-1-32B-Q4_K_S.gguf` | Q4_K_S       | 17.48     | Smaller, slightly more aggressive quantization                 |
+
+Choose a variant based on your hardware and quality requirements:
+
+- **Q4_K_M / Q4_K_S**: best options for low‑VRAM environments.  
+- **Q6_K / Q8_0**: better fidelity for demanding generation quality or professional use.  
+
+*Note: Try adding the `/think` tag to your prompts if you want to explicitly trigger reasoning capabilities.*
+
+---
+
+## Usage with `LM Studio`
+
+1. Download LM Studio from [here](https://lmstudio.ai/).
+2. Search for "NuisanceValue/MetalGPT-1-GGUF" in the model hub within LM Studio.
+3. Select a quantization variant.
+4. Once downloaded, select the model in the menu.  
+
+
+## Usage with `llama.cpp`
+
+Download one of the GGUF files (for example `MetalGPT-1-32B-Q4_K_M.gguf`) and run:
+```bash
+./llama-cli \
+  -m MetalGPT-1-32B-Q4_K_M.gguf \
+  -p "Назови плюсы и минусы хлоридной и сульфатной технологии производства никеля." \
+  --temp 0.7 \
+  --top-p 0.8 \
+  --top-k 70 \
+  --n-predict 512 \
+  --ctx-size 8192
+```
+
+
+## Usage with `llama-cpp-python`
+
+Install `llama-cpp-python` if you haven't already:
+```bash
+pip install llama-cpp-python
+```
+
+Then use the following code snippet to load the model and generate text:
+```python
+from llama_cpp import Llama
+
+# Path to your GGUF file
+model_path = "MetalGPT-1-32B-Q4_K_M.gguf"
+
+# Initialize the model
+llm = Llama(
+    model_path=model_path,
+    n_gpu_layers=-1,      # Offload all layers to GPU
+    n_ctx=8192,           # Context window (adjust based on VRAM)
+    verbose=False
+)
+
+messages = [
+    {"role": "system", "content": "Ты специалист в области металлургии."},
+    {"role": "user", "content": "Назови плюсы и минусы хлоридной и сульфатной технологии производства никеля."},
+]
+
+output = llm.create_chat_completion(
+    messages=messages,
+    max_tokens=2048,
+    temperature=0.7,
+    top_p=0.8
+)
+
+print(output["choices"][0]["message"]["content"])
+```
+