diff --git a/.gitattributes b/.gitattributes
index b7e9e3a..624dd08 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -1,37 +1,49 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin 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
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*.tfevents* filter=lfs diff=lfs merge=lfs -text
-*.db* filter=lfs diff=lfs merge=lfs -text
-*.ark* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.gguf* filter=lfs diff=lfs merge=lfs -text
-*.ggml filter=lfs diff=lfs merge=lfs -text
-*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q2_K.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q2_K.gguf
new file mode 100644
index 0000000..3df95de
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e281023b24f130599fef228b96cf00701768655e68dbb0893eb642cd3bef3359
+size 3179131136
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_L.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_L.gguf
new file mode 100644
index 0000000..d4dc977
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2bc55ae5666925bad1767f2b6bd01b901872d7ff9ba071e544c0dc05cf4ca7
+size 4321956096
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_M.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_M.gguf
new file mode 100644
index 0000000..43c6736
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997536f7bc8800348fbdd059dc0115dc303fe34ca5957537fd13c24fe1314086
+size 4018917632
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_S.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_S.gguf
new file mode 100644
index 0000000..1b6e15b
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0ae6bd847afb7fc72230425bae31f5f37924a381be5e4ffe599b9ebabff555
+size 3664498944
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_0.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_0.gguf
new file mode 100644
index 0000000..7cfa33d
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82101a5e60419e23519aa2f42542b9c64074048085ccc33487c2c6c3356994e
+size 4661211392
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_1.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_1.gguf
new file mode 100644
index 0000000..520d67a
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4ec0990b44779fec29060c6ade65b038e3a176f86fbb70f998932c22eab9fc
+size 5130252544
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_M.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_M.gguf
new file mode 100644
index 0000000..c16e151
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a1dc9f01bbcfa56fdb271f8a8af65b4dc93fbf7bc387b98d2fc64c368f3f42
+size 4920733952
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_S.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_S.gguf
new file mode 100644
index 0000000..d3fba53
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c600482b5d0abecba870e51ed9e65c5e3e0c9c17d1c4390274487200603858a
+size 4692668672
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_0.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_0.gguf
new file mode 100644
index 0000000..6a8cee5
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9efd0a600b6273c9feebd8c709639baa11691940ea174447e17d26d72b9c59cb
+size 5599293696
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_1.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_1.gguf
new file mode 100644
index 0000000..63cdebf
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702ee1bd8ca7cb930bedc0ed283b69ccafdf272fad3cf2f0e6161184a0d1bd19
+size 6068334848
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_M.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_M.gguf
new file mode 100644
index 0000000..c93c560
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99eab0fa74ceb78f52820310d3caa3fd481851576f6a2b283bf2a124a4f6ac7
+size 5732987136
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_S.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_S.gguf
new file mode 100644
index 0000000..bcf8343
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a2166551b4d733aa309615c7aa12420463b396478fed60fdc12a60c3631bcc
+size 5599293696
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q6_K.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q6_K.gguf
new file mode 100644
index 0000000..8f1b8bf
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed72a1aad4c6898024ac0191d27d9766afd71d496c513299ef8af21a640512cc
+size 6596006144
diff --git a/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q8_0.gguf b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q8_0.gguf
new file mode 100644
index 0000000..1797bce
--- /dev/null
+++ b/Meta-Llama-3-8B-Instruct-function-calling-json-mode.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81cc54c5c73bd6cc5b3f9e6889bf69d61ed68b2fc85eb251695af15da7f09df
+size 8540770560
diff --git a/README.md b/README.md
index 5fa08bd..feedfb3 100644
--- a/README.md
+++ b/README.md
@@ -1,47 +1,163 @@
 ---
-license: Apache License 2.0
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
+library_name: transformers
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- trl
+- llama
+language:
+- en
+base_model: hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode
+pipeline_tag: text-generation
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
-```
+# QuantFactory/Meta-Llama-3-8B-Instruct-function-calling-json-mode-GGUF
+This is quantized version of [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode) created using llama.cpp
+
+## Model Description
+
+This model was fine-tuned on meta-llama/Meta-Llama-3-8B-Instruct for function calling and json mode.
+
+## Usage
+### JSON Mode
 ```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('QuantFactory/Meta-Llama-3-8B-Instruct-function-calling-json-mode-GGUF')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/QuantFactory/Meta-Llama-3-8B-Instruct-function-calling-json-mode-GGUF.git
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant, answer in JSON with key \"message\""},
+    {"role": "user", "content": "Who are you?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+# >> {"message": "I am a helpful assistant, with access to a vast amount of information. I can help you with tasks such as answering questions, providing definitions, translating text, and more. Feel free to ask me anything!"}
 ```
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
\ No newline at end of file
+### Function Calling
+Function calling requires two step inferences, below is the example:
+
+## Step 1:
+
+```python
+functions_metadata = [
+    {
+      "type": "function",
+      "function": {
+        "name": "get_temperature",
+        "description": "get temperature of a city",
+        "parameters": {
+          "type": "object",
+          "properties": {
+            "city": {
+              "type": "string",
+              "description": "name"
+            }
+          },
+          "required": [
+            "city"
+          ]
+        }
+      }
+    }
+]
+
+messages = [
+    { "role": "system", "content": f"""You are a helpful assistant with access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }} </functioncall>\n\nEdge cases you must handle:\n - If there are no functions that match the user request, you will respond politely that you cannot help."""},
+    { "role": "user", "content": "What is the temperature in Tokyo right now?"}
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+# >> <functioncall> {"name": "get_temperature", "arguments": '{"city": "Tokyo"}'} </functioncall>"""}
+```
+## Step 2:
+
+```python
+messages = [
+    { "role": "system", "content": f"""You are a helpful assistant with access to the following functions: \n {str(functions_metadata)}\n\nTo use these functions respond with:\n<functioncall> {{ "name": "function_name", "arguments": {{ "arg_1": "value_1", "arg_1": "value_1", ... }} }} </functioncall>\n\nEdge cases you must handle:\n - If there are no functions that match the user request, you will respond politely that you cannot help."""},
+    { "role": "user", "content": "What is the temperature in Tokyo right now?"},
+    # You will get the previous prediction, extract it will the tag <functioncall>
+    # execute the function and append it to the messages like below:
+    { "role": "assistant", "content": """<functioncall> {"name": "get_temperature", "arguments": '{"city": "Tokyo"}'} </functioncall>"""},    
+    { "role": "user", "content": """<function_response> {"temperature":30 C} </function_response>"""}
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+# >> The current temperature in Tokyo is 30 degrees Celsius.
+```
+
+# Uploaded  model
+
+- **Developed by:** hiieu
+
+This model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
\ No newline at end of file
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file