初始化项目，由ModelHub XC社区提供模型

Model: Mwanzau/Mazgu_Llama-1B-V2-Knowledge-16bit
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: unsloth/Llama-3.2-1B-Instruct
+tags:
+- safetensors
+- llama-3
+- merged
+- tumbuka
+- bantu
+- malawi
+language:
+- tum
+- en
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Mazgu_Llama-1B-V2-Knowledge-16bit (Standalone Model)
+
+**Mazgu_Llama-1B-V2-Knowledge-16bit** is a fully merged, standalone 16-bit `model.safetensors` release of Llama-3-1B, fine-tuned specifically for the Tumbuka language. 
+
+Because the LoRA weights are merged directly into the base architecture, this repository **does not require loading external adapter weights at runtime**. It serves as an ideal baseline for:
+* Direct inference via Hugging Face `transformers` or `vLLM`.
+* Continual pre-training or further SFT runs.
+* Full-model export and custom quantization pipelines.
+
+---
+
+## 💻 Quickstart Guide
+
+### Option 1: Standard Transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Mwanzau/Mazgu_Llama-1B-V2-Knowledge-16bit"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+prompt = "### Instruction:\nLongosolani vya Yesu mu Mateyo 24.\n\n### Response:\n"
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=150,
+    temperature=0.6,
+    repetition_penalty=1.2
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+---
+
+### Option 2: Optimized 4-Bit Loading with Unsloth (Colab / Kaggle)
+
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+    model_name = "Mwanzau/Mazgu_Llama-1B-V2-Knowledge-16bit",
+    max_seq_length = 2048,
+    load_in_4bit = True, # Saves VRAM on T4 GPUs
+)
+
+FastLanguageModel.for_inference(model)
+
+prompt = "### Instruction:\nLongosolani vyakurya ivyo vili bwino ku munda.\n\n### Response:\n"
+inputs = tokenizer([prompt], return_tensors="pt").to("cuda")
+
+outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.6, repetition_penalty=1.2)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+
+---
+
+### 📊 Summary
+Format: Unsharded Native safetensors
+Precision: 16-bit Float (bfloat16/float16)
+Vocabulary Focus: Tumbuka instruction-following and factual knowledge retrieval.
+
+

config.json

@@ -0,0 +1,36 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 128000,
+    "torch_dtype": "float16",
+    "eos_token_id": 128001,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 8,
+    "pad_token_id": 128001,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+        "factor": 32.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_theta": 500000.0,
+        "rope_type": "llama3"
+    },
+    "tie_word_embeddings": true,
+    "unsloth_version": "2026.7.5",
+    "use_cache": true,
+    "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001
+  ],
+  "max_length": 131072,
+  "pad_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.5.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4232aea9e3754465d2a75a4e7dc31c926fbc29a8d3b2be4990ec57b85373bf
+size 2471645464