初始化项目，由ModelHub XC社区提供模型

Model: solidrust/Llama-3-16B-Instruct-v0.1-AWQ
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,63 @@
+---
+base_model: MaziyarPanahi/Llama-3-16B-Instruct-v0.1
+library_name: transformers
+tags:
+- 4-bit
+- AWQ
+- text-generation
+- autotrain_compatible
+- endpoints_compatible
+  - mergekit
+  - merge
+  - facebook
+  - meta
+  - pytorch
+  - llama
+  - llama-3
+language:
+  - en
+pipeline_tag: text-generation
+license: other
+license_name: llama3
+license_link: LICENSE
+inference: false
+model_creator: MaziyarPanahi
+model_name: Llama-3-16B-Instruct-v0.1
+quantized_by: Suparious
+---
+# MaziyarPanahi/Llama-3-16B-Instruct-v0.1 AWQ
+
+- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)
+- Original model: [Llama-3-16B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-16B-Instruct-v0.1)
+
+<img src="./llama-3-merges.webp" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+
+## Model Summary
+
+This model is a self-merge of `MaziyarPanahi/Llama-3-11B-Instruct-v0.1` model.
+
+## Prompt template
+
+```text
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+what's 25-4*2+3<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+To evaluate this expression, we need to follow the order of operations (PEMDAS):
+
+1. First, multiply 4 and 2: 4*2 = 8
+2. Then, subtract 8 from 25: 25 - 8 = 17
+3. Finally, add 3: 17 + 3 = 20
+
+So, 25-4*2+3 = 20!<|eot_id|>
+To evaluate this expression, we need to follow the order of operations (PEMDAS):
+
+1. First, multiply 4 and 2: 4*2 = 8
+2. Then, subtract 8 from 25: 25 - 8 = 17
+3. Finally, add 3: 17 + 3 = 20
+
+So, 25-4*2+3 = 20!
+```
+

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--MaziyarPanahi--Llama-3-16B-Instruct-v0.1/snapshots/c39c7b950e74e22cdf4a5e16253ada97cf27a43a",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "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": 72,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "transformers_version": "4.38.2",
+  "use_cache": false
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:accc087ac8e0a9c990a7ba112ced3223b92ec9fada30f5c9ef6ac629c6ee6bac
+size 4986725320

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9544b5260c04247f3c4356ffc79ea876b186744a27cff84a92233ab4a6090470
+size 4223770032

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8005050c5e27c8232d9ce04f03631ce67bcc362c80fc57079bda23b498695c20
+size 1050673280

quant_config.json

@@ -0,0 +1,6 @@
+{
+  "zero_point": true,
+  "q_group_size": 128,
+  "w_bit": 4,
+  "version": "GEMM"
+}

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": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}