初始化项目，由ModelHub XC社区提供模型

Model: Deci/DeciLM-7B-instruct-GGUF
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
+decilm-7b-uniform-gqa-f16.gguf filter=lfs diff=lfs merge=lfs -text
+decilm-7b-uniform-gqa-f32.gguf filter=lfs diff=lfs merge=lfs -text
+decilm-7b-uniform-gqa-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+---
+
+# DeciLM-7B-instruct GGUF checkpoints
+This repository includes <a href="https://huggingface.co/Deci/DeciLM-7B-instruct">Deci/DeciLM-7B-instruct</a> checkpoints in the <b>GGUF</b> format.<br>
+DeciLM demonstrates strong performance on commodity CPUs when utilizing the llama.cpp codebase.
+
+## 1. Clone and build llama.cpp (1 minute)
+```
+git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make -j
+```
+
+## 2. Download the GGUF checkpoint
+- Navigate to the 'Files' section
+  - Click on 'decilm-7b-uniform-gqa-q8_0.gguf'
+    - Click on the 'Download' button
+
+## 3. Generate outputs
+- Use the chat template and feed a prompt to DeciLM-7B-instruct. We are using the INT8 quantized GGUF checkpoint.
+    ```text
+    ./main -m ~/Downloads/decilm-7b-uniform-gqa-q8_0.gguf -p """
+    ### System:
+    You are an AI assistant that follows instructions exceptionally well. Be as helpful as possible.
+    ### User:
+    How do I make the most delicious pancakes the world has ever tasted?
+    ### Assistant:
+    """
+    ```
+
+- Output:
+    ```
+    ### System:
+    You are an AI assistant that follows instructions exceptionally well. Be as helpful as possible.
+    ### User:
+    How do I make the most delicious pancakes the world has ever tasted?
+    ### Assistant:
+     To make the most delicious pancakes (pancakes) the world has ever tasted, here are some steps you can follow:
+    
+    
+    Ingreat ingredients:
+    - 1 cup all-purpose flour (maida flour)- 1/4 cup sugar (granhana or raw white)
+    - 2 egg yolks
+    - 1/2 cup milk-2 tabls melted butter (or oil)-2 tsp vanila
+    - 2 tsps baking powder
+    - salt (a little)
+
+    Mixing:
+    1. Combine the flour, sugar and salt in a large mixing bowl. Add egg yolks, butter or oil, and vanilla to the mixture, stirring well.
+    2. Pour in milk gradually while blending (with mixer).
+    3. Beat with the batter till smooth, then add baking powder.
+
+    Cooking:
+    4. Heat a nonstick pan with little butter or oil, pour 1/4 cup of batter (or 5 inch) for each pancake. Cook over medium heat, until bubble rises on top surface. Flip and cook the other side till golden.  [end of text]
+    
+    llama_print_timings:        load time =     325.09 ms
+    llama_print_timings:      sample time =      19.99 ms /   249 runs   (    0.08 ms per token, 12454.98 tokens per second)
+    llama_print_timings: prompt eval time =     239.66 ms /    52 tokens (    4.61 ms per token,   216.97 tokens per second)
+    llama_print_timings:        eval time =   11227.83 ms /   248 runs   (   45.27 ms per token,    22.09 tokens per second)
+    llama_print_timings:       total time =   11517.22 ms
+    ggml_metal_free: deallocating
+    Log end
+    ```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "DeciLMForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_bfloat16": true,
+  "use_cache": true,
+  "vocab_size": 32000
+}

decilm-7b-uniform-gqa-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c28d32a79f4dea3cf931b40237b64ce9109efd7e6c8a990a8c611286b9b2341f
+size 14217232832

decilm-7b-uniform-gqa-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45f3e8a5e05b557c6f8c421d47f2a3226af912016f923150ae07789977ba4cc
+size 28430792256

decilm-7b-uniform-gqa-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b60beae4c9d5d7131f846f7545cb386e20d8f2c613844a0142ee701537dbfe3
+size 7554187712