初始化项目，由ModelHub XC社区提供模型

Model: CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,48 @@
+*.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
+Mistral-7B-Instruct-v0.3.fp16.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.imatrix.dat filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Mistral-7B-Instruct-v0.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text

Mistral-7B-Instruct-v0.3.IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1a2dd797732b2bd81522c0dc2ce07f02c9a760f760e16302dda6477d1b7b59
+size 1757664288

Mistral-7B-Instruct-v0.3.IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a3cfd34d22263ccf49dfc02e7f3ea7c983118680a9dedca31817efdbd3efab
+size 1615320096

Mistral-7B-Instruct-v0.3.IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e93031a8c059e014a904b2f8cebdf073ff7310f9a6d2579c07c8d6ebdc6d8ae
+size 2504250400

Mistral-7B-Instruct-v0.3.IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2afeb6b4536c43014c5575aed66ce0577c965b9bf5019bc7c43cdbbaf520bc4a
+size 2314458144

Mistral-7B-Instruct-v0.3.IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff8d8d252da2955e69420ddf6ba79c7f9364c52a269d3333edefb6ca4e58bac
+size 2201474080

Mistral-7B-Instruct-v0.3.IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebea120c9f96af5595fbb1b7addc8daa7841bfcf16703d0382d21b22e66a8e5
+size 1994904608

Mistral-7B-Instruct-v0.3.IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d49160a4dbf6af69ab8a22bcee90d821e724aa0deddd63c2625f60eaeff4af4
+size 3288847392

Mistral-7B-Instruct-v0.3.IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156cbd42ee5a635bb795dc36bd3283d7c746b2e12bfcd451163756a283345e0c
+size 3186349088

Mistral-7B-Instruct-v0.3.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84985ba223dc145565068e1d1b617cc44201c46ad87b009c7281e708613bf484
+size 3022771232

Mistral-7B-Instruct-v0.3.IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26233eb5e3fc54bbdfe977934ef7b015dd5dac759e424710f024fc795781027c
+size 2830881824

Mistral-7B-Instruct-v0.3.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0afba232e1e46573db08bd965c82ef583f0b71131be840a19982339d94e067c
+size 3911963680

Mistral-7B-Instruct-v0.3.fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd62e09c7201d790605d3a8be94260bfbecd70c470ed297e4d584fa319ed8ab
+size 14497338144

Mistral-7B-Instruct-v0.3.imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44d933bda5232dd9081c20e0ae2ef2df5aab5c4388fc308b237d1454e694e81
+size 4988162

README.md

@@ -0,0 +1,290 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+language:
+- en
+pipeline_tag: text-generation
+license: apache-2.0
+model_creator: Mistral AI
+model_name: Mistral-7B-Instruct-v0.3
+model_type: mistral
+quantized_by: CISC
+---
+
+# Mistral-7B-Instruct-v0.3 - SOTA GGUF
+- Model creator: [Mistral AI](https://huggingface.co/mistralai)
+- Original model: [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
+
+<!-- description start -->
+## Description
+
+This repo contains State Of The Art quantized GGUF format model files for [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3).
+
+Quantization was done with an importance matrix that was trained for ~1M tokens (256 batches of 4096 tokens) of [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) and [wiki.train.raw](https://raw.githubusercontent.com/pytorch/examples/main/word_language_model/data/wikitext-2/train.txt) concatenated.
+
+The embedded chat template has been extended to support function calling via OpenAI-compatible `tools` parameter, see [example](#simple-llama-cpp-python-example-function-calling-code).
+
+<!-- description end -->
+
+
+<!-- prompt-template start -->
+## Prompt template: Mistral v3
+
+```
+[AVAILABLE_TOOLS] [{"name": "function_name", "description": "Description", "parameters": {...}}, ...][/AVAILABLE_TOOLS][INST] {prompt}[/INST]
+```
+
+<!-- prompt-template end -->
+
+
+<!-- compatibility_gguf start -->
+## Compatibility
+
+These quantised GGUFv3 files are compatible with llama.cpp from February 27th 2024 onwards, as of commit [0becb22](https://github.com/ggerganov/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307)
+
+They are also compatible with many third party UIs and libraries provided they are built using a recent llama.cpp.
+
+## Explanation of quantisation methods
+
+<details>
+  <summary>Click to see details</summary>
+
+The new methods available are:
+
+* GGML_TYPE_IQ1_S - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.56 bits per weight (bpw)
+* GGML_TYPE_IQ1_M - 1-bit quantization in super-blocks with an importance matrix applied, effectively using 1.75 bpw
+* GGML_TYPE_IQ2_XXS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.06 bpw
+* GGML_TYPE_IQ2_XS - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.31 bpw
+* GGML_TYPE_IQ2_S - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.5 bpw
+* GGML_TYPE_IQ2_M - 2-bit quantization in super-blocks with an importance matrix applied, effectively using 2.7 bpw
+* GGML_TYPE_IQ3_XXS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.06 bpw
+* GGML_TYPE_IQ3_XS - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.3 bpw
+* GGML_TYPE_IQ3_S - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.44 bpw
+* GGML_TYPE_IQ3_M - 3-bit quantization in super-blocks with an importance matrix applied, effectively using 3.66 bpw
+* GGML_TYPE_IQ4_XS - 4-bit quantization in super-blocks with an importance matrix applied, effectively using 4.25 bpw
+* GGML_TYPE_IQ4_NL - 4-bit non-linearly mapped quantization with an importance matrix applied, effectively using 4.5 bpw
+
+Refer to the Provided Files table below to see what files use which methods, and how.
+</details>
+<!-- compatibility_gguf end -->
+
+<!-- README_GGUF.md-provided-files start -->
+## Provided files
+
+| Name | Quant method | Bits | Size | Max RAM required | Use case |
+| ---- | ---- | ---- | ---- | ---- | ----- |
+| [Mistral-7B-Instruct-v0.3.IQ1_S.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ1_S.gguf) | IQ1_S | 1 | 1.5 GB| 2.5 GB | smallest, significant quality loss - **TBD**: Waiting for [this issue](https://github.com/ggerganov/llama.cpp/issues/5996) to be resolved |
+| [Mistral-7B-Instruct-v0.3.IQ1_M.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ1_M.gguf) | IQ1_M | 1 | 1.6 GB| 2.6 GB | very small, significant quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ2_XXS.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ2_XXS.gguf) | IQ2_XXS | 2 | 1.8 GB| 2.8 GB | very small, high quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ2_XS.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ2_XS.gguf) | IQ2_XS | 2 | 1.9 GB| 2.9 GB | very small, high quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ2_S.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ2_S.gguf) | IQ2_S | 2 | 2.1 GB| 3.1 GB | small, substantial quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ2_M.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ2_M.gguf) | IQ2_M | 2 | 2.2 GB| 3.2 GB | small, greater quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ3_XXS.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ3_XXS.gguf) | IQ3_XXS | 3 | 2.5 GB| 3.5 GB | very small, high quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ3_XS.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ3_XS.gguf) | IQ3_XS | 3 | 2.7 GB| 3.7 GB | small, substantial quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ3_S.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ3_S.gguf) | IQ3_S | 3 | 2.8 GB| 3.8 GB | small, greater quality loss |
+| [Mistral-7B-Instruct-v0.3.IQ3_M.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ3_M.gguf) | IQ3_M | 3 | 3.0 GB| 4.0 GB | medium, balanced quality - recommended |
+| [Mistral-7B-Instruct-v0.3.IQ4_XS.gguf](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.IQ4_XS.gguf) | IQ4_XS | 4 | 3.4 GB| 4.4 GB | small, substantial quality loss |
+
+Generated importance matrix file: [Mistral-7B-Instruct-v0.3.imatrix.dat](https://huggingface.co/CISCai/Mistral-7B-Instruct-v0.3-SOTA-GGUF/blob/main/Mistral-7B-Instruct-v0.3.imatrix.dat)
+
+**Note**: the above RAM figures assume no GPU offloading with 4K context. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
+
+<!-- README_GGUF.md-provided-files end -->
+
+<!-- README_GGUF.md-how-to-run start -->
+## Example `llama.cpp` command
+
+Make sure you are using `llama.cpp` from commit [0becb22](https://github.com/ggerganov/llama.cpp/commit/0becb22ac05b6542bd9d5f2235691aa1d3d4d307) or later.
+
+```shell
+./main -ngl 33 -m Mistral-7B-Instruct-v0.3.IQ4_XS.gguf --color -c 32768 --temp 0 --repeat-penalty 1.1 -p "[AVAILABLE_TOOLS] {tools}[/AVAILABLE_TOOLS][INST] {prompt}[/INST]"
+```
+
+Change `-ngl 33` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
+
+Change `-c 32768` to the desired sequence length.
+
+If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
+
+If you are low on V/RAM try quantizing the K-cache with `-ctk q8_0` or even `-ctk q4_0` for big memory savings (depending on context size).
+There is a similar option for V-cache (`-ctv`), however that is [not working yet](https://github.com/ggerganov/llama.cpp/issues/4425).
+
+For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
+
+## How to run from Python code
+
+You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) module.
+
+### How to load this model in Python code, using llama-cpp-python
+
+For full documentation, please see: [llama-cpp-python docs](https://llama-cpp-python.readthedocs.io/en/latest/).
+
+#### First install the package
+
+Run one of the following commands, according to your system:
+
+```shell
+# Prebuilt wheel with basic CPU support
+pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+# Prebuilt wheel with NVidia CUDA acceleration
+pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 (or cu122 etc.)
+# Prebuilt wheel with Metal GPU acceleration
+pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal
+# Build base version with no GPU acceleration
+pip install llama-cpp-python
+# With NVidia CUDA acceleration
+CMAKE_ARGS="-DLLAMA_CUDA=on" pip install llama-cpp-python
+# Or with OpenBLAS acceleration
+CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
+# Or with CLBLast acceleration
+CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
+# Or with AMD ROCm GPU acceleration (Linux only)
+CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
+# Or with Metal GPU acceleration for macOS systems only
+CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
+# Or with Vulkan acceleration
+CMAKE_ARGS="-DLLAMA_VULKAN=on" pip install llama-cpp-python
+# Or with Kompute acceleration
+CMAKE_ARGS="-DLLAMA_KOMPUTE=on" pip install llama-cpp-python
+# Or with SYCL acceleration
+CMAKE_ARGS="-DLLAMA_SYCL=on -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx" pip install llama-cpp-python
+
+# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
+$env:CMAKE_ARGS = "-DLLAMA_CUDA=on"
+pip install llama-cpp-python
+```
+
+#### Simple llama-cpp-python example code
+
+```python
+from llama_cpp import Llama
+
+# Chat Completion API
+
+llm = Llama(model_path="./Mistral-7B-Instruct-v0.3.IQ4_XS.gguf", n_gpu_layers=33, n_ctx=32768)
+print(llm.create_chat_completion(
+    messages = [
+        {
+            "role": "user",
+            "content": "Pick a LeetCode challenge and solve it in Python."
+        }
+    ]
+))
+```
+
+#### Simple llama-cpp-python example function calling code
+
+```python
+from llama_cpp import Llama
+
+# Chat Completion API
+
+grammar = LlamaGrammar.from_json_schema(json.dumps({
+    "type": "array",
+    "items": {
+        "type": "object",
+        "required": [ "name", "arguments" ],
+        "properties": {
+            "name": {
+                "type": "string"
+            },
+            "arguments": {
+                "type": "object"
+            }
+        }
+    }
+}))
+
+llm = Llama(model_path="./Mistral-7B-Instruct-v0.3.IQ4_XS.gguf", n_gpu_layers=33, n_ctx=32768)
+response = llm.create_chat_completion(
+      temperature = 0.0,
+      repeat_penalty = 1.1,
+      messages = [
+        {
+          "role": "user",
+          "content": "What's the weather like in Oslo and Stockholm?"
+        }
+      ],
+      tools=[{
+        "type": "function",
+        "function": {
+          "name": "get_current_weather",
+          "description": "Get the current weather in a given location",
+          "parameters": {
+            "type": "object",
+            "properties": {
+              "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA"
+              },
+              "unit": {
+                "type": "string",
+                "enum": [ "celsius", "fahrenheit" ]
+              }
+            },
+            "required": [ "location" ]
+          }
+        }
+      }],
+      grammar = grammar
+)
+print(json.loads(response["choices"][0]["text"]))
+
+print(llm.create_chat_completion(
+      temperature = 0.0,
+      repeat_penalty = 1.1,
+      messages = [
+        {
+          "role": "user",
+          "content": "What's the weather like in Oslo?"
+        },
+        { # The tool_calls is from the response to the above with tool_choice active
+          "role": "assistant",
+          "content": None,
+          "tool_calls": [
+            {
+              "id": "call__0_get_current_weather_cmpl-...",
+              "type": "function",
+              "function": {
+                "name": "get_current_weather",
+                "arguments": '{ "location": "Oslo, NO" ,"unit": "celsius"} '
+              }
+            }
+          ]
+        },
+        { # The tool_call_id is from tool_calls and content is the result from the function call you made
+          "role": "tool",
+          "content": "20",
+          "tool_call_id": "call__0_get_current_weather_cmpl-..."
+        }
+      ],
+      tools=[{
+        "type": "function",
+        "function": {
+          "name": "get_current_weather",
+          "description": "Get the current weather in a given location",
+          "parameters": {
+            "type": "object",
+            "properties": {
+              "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA"
+              },
+              "unit": {
+                "type": "string",
+                "enum": [ "celsius", "fahrenheit" ]
+              }
+            },
+            "required": [ "location" ]
+          }
+        }
+      }],
+      #tool_choice={
+      #  "type": "function",
+      #  "function": {
+      #    "name": "get_current_weather"
+      #  }
+      #}
+))
+```
+
+<!-- README_GGUF.md-how-to-run end -->