初始化项目，由ModelHub XC社区提供模型

Model: teddylee777/llama-3-8b-it-ko-chang-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,44 @@
+*.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
+llama-3-8b-it-ko-chang-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-it-ko-chang-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+license: apache-2.0
+language:
+- ko
+---
+
+- Original model is [lcw99/llama-3-8b-it-ko-chang](https://huggingface.co/lcw99/llama-3-8b-it-ko-chang)
+- Quantized by [teddylee777](https://huggingface.co/teddylee777) by using [llama.cpp](https://github.com/ggerganov/llama.cpp)
+
+## Template (LM Studio)
+
+```
+<|start_header_id|>system<|end_header_id|>
+{System}
+<|eot_id|>
+<|start_header_id|>B<|end_header_id|>
+{User}
+<|eot_id|><|start_header_id|>A<|end_header_id|>
+{Assistant}
+```
+
+### LM Studio Demo
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/649d86964ee9d3611f71f39e/oBr-a6-hf0frsKwtDDafL.png)
+
+
+## Ollama Template
+
+```
+TEMPLATE """{{- if .System }}<|start_header_id|>system<|end_header_id|>
+{{ .System }}
+<|eot_id|>
+{{- end }}
+
+<|start_header_id|>B<|end_header_id|>
+{{ .Prompt }}
+<|eot_id|>
+<|start_header_id|>A<|end_header_id|>
+"""
+```
+
+### Ollama DEMO
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/649d86964ee9d3611f71f39e/fed4vqNcjQPW3WuzPjgKv.png)
+
+## Stop Token
+
+```
+<|eot_id|>
+<|start_header_id|>
+<|end_header_id|>
+<|begin_of_text|> 
+<|end_of_text|>
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "lcw99/llama-3-8b-it-ko-chang",
+  "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": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

llama-3-8b-it-ko-chang-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aff1533ad2dc5fbb3c19ca40338aaae90b7d3abfe3fea1f7540d349973534c
+size 4661211424

llama-3-8b-it-ko-chang-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94af7ce179cc7229606bf740f57c4dd522681a51aa1eac7f3c30719ed4d9cabd
+size 5130252576

llama-3-8b-it-ko-chang-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:682a45ae2bcb7877c0851bc8ae4ce8e9826ce8271b8babf307aa4a2cfdb91f91
+size 4920733984

llama-3-8b-it-ko-chang-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74ea60de81245d647a54ea8f13e69f11fc238af4c757c3023cbf9b0d05a35ec
+size 4692668704

llama-3-8b-it-ko-chang-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e840e01707e23ede4129ab28811aaa0f0bdbda214967b488c4d1ec2ced68174
+size 5599293728

llama-3-8b-it-ko-chang-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1548a7bc6bdeda41326f13750bff2a767bb6dec05109d74547979af5dbb21cf
+size 5732987168

llama-3-8b-it-ko-chang-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784374f336ffba0f22b8fddd308825eb3a3b44ce745e7b448aebae1acf168f83
+size 5599293728

llama-3-8b-it-ko-chang-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493207e7a8f2ecef97fb836721261f4493c31098d6f220786a17246b863a25fa
+size 6596006176

llama-3-8b-it-ko-chang-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01590a4cbcb3fc5a5544fa1a9243b9f09187ee10941dde8e25495d1a6ad168a4
+size 8540770592

llama_3_it_ko_chang_7b.preset.json

@@ -0,0 +1,58 @@
+{
+  "name": "llama-3-it-ko-chang-7b",
+  "load_params": {
+    "n_ctx": 4096,
+    "n_batch": 512,
+    "rope_freq_base": 0,
+    "rope_freq_scale": 0,
+    "n_gpu_layers": -1,
+    "use_mlock": true,
+    "main_gpu": 0,
+    "tensor_split": [
+      0
+    ],
+    "seed": -1,
+    "f16_kv": true,
+    "use_mmap": true,
+    "no_kv_offload": false,
+    "num_experts_used": 0
+  },
+  "inference_params": {
+    "n_threads": 4,
+    "n_predict": -1,
+    "top_k": 40,
+    "min_p": 0.05,
+    "top_p": 0.95,
+    "temp": 0,
+    "repeat_penalty": 1.1,
+    "input_prefix": "<|start_header_id|>B<|end_header_id|>\n\n",
+    "input_suffix": "<|eot_id|><|start_header_id|>A<|end_header_id|>\n\n",
+    "antiprompt": [
+      "<|start_header_id|>",
+      "<|eot_id|>",
+      "<|end_header_id|>",
+      "<|begin_of_text|>",
+      "<|end_of_text|>",
+      "B:",
+      "<|start_header_id|>B:<|end_header_id|>\\n\\n",
+      "<|start_header_id|>B<|end_header_id|>\\n\\n"
+    ],
+    "pre_prompt": "You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability.",
+    "pre_prompt_suffix": "<|eot_id|>",
+    "pre_prompt_prefix": "<|start_header_id|>system<|end_header_id|>\\n\\n",
+    "seed": -1,
+    "tfs_z": 1,
+    "typical_p": 1,
+    "repeat_last_n": 64,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+    "n_keep": 0,
+    "logit_bias": {},
+    "mirostat": 0,
+    "mirostat_tau": 5,
+    "mirostat_eta": 0.1,
+    "memory_f16": true,
+    "multiline_input": false,
+    "penalize_nl": true
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": "$"
+}