初始化项目，由ModelHub XC社区提供模型

Model: meditsolutions/Llama-3.2-SUN-1B-chat
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+medit-sun-1B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+language:
+- en
+license: llama3.2
+library_name: transformers
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
+- Llama-3.2-SUN-2.5B-chat
+datasets:
+- argilla/OpenHermesPreferences
+- argilla/magpie-ultra-v0.1
+- argilla/Capybara-Preferences-Filtered
+- mlabonne/open-perfectblend
+- HuggingFaceTB/everyday-conversations-llama3.1-2k
+- WizardLMTeam/WizardLM_evol_instruct_V2_196k
+- ProlificAI/social-reasoning-rlhf
+pipeline_tag: text-generation
+
+---
+
+# MedIT SUN 1B
+
+<div align="center">
+  <img src="https://i.ibb.co/PF0TdMJ/imagine-image-9a56cee7-0f4f-4cc2-b265-a5b8d04f266b.png" alt="Llama-3.2-MedIT-SUN-2.5B" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;">
+</div>
+
+**Base Model**
+- Llama 3.2 1B -> MedIT SUN 2.5B -> MedIT SUN 1B
+
+**Mesh Size**
+- 1B to 2.5B parameters [MedIT SUN 2.5B](https://huggingface.co/meditsolutions/Llama-3.2-SUN-2.5B-chat) -> layers mesh using MedIT-mesh technique and downscaled to 1B
+
+**Extension Method**
+- Proprietary technique developed by MedIT Solutions
+
+**Fine-tuning**
+- Open (or open subsets allowing for commercial use) open datasets from HF
+- Open (or open subsets allowing for commercial use) SFT datasets from HF
+
+**Training Status**   
+- Current version: chat-1.0.0
+
+**Key Features**
+- Built on Llama 3.2 architecture
+- Upscaled from 1B to 2.47B parameters
+- Optimized for open-ended conversations
+- Incorporates supervised fine-tuning for improved performance
+- Layers meshing using the MedIT-mesh technique
+- Downscaled to 1B
+
+**Use Case**
+- General conversation and task-oriented interactions
+
+**Limitations**
+As the model is still in training, performance and capabilities may vary. Users should be aware that the model is not in its final form and may exhibit inconsistencies or limitations typical of in-progress AI models.
+
+**Disclaimer and Safety Considerations**
+The Model is designed to be used as a smart assistant but not as a knowledge source within your applications, systems, or environments. It is not intended to provide 100% accurate answers, especially in scenarios where high precision and accuracy are 

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "/home/mkurman/gitlab/ai/model-trainer/checkpoints/llama_2_4b_2/chat-2.5B_base_instruct_merge_final_0.9995-sml-merge",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_down_scaling": null,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "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": 128004,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.10.7",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "max_length": 131072,
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.1"
+}

medit-sun-1B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b474a92a8fa93b8be248e054887b79a751091344669c254ecf62f9e696187104
+size 1600167520

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37471860a27d16b35154d2c0f8e3f9307bf82a80ce46f6b5361eb339e8968d2c
+size 2996982344

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}