初始化项目，由ModelHub XC社区提供模型

Model: duyntnet/Phi-3.5-mini-instruct-imatrix-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,62 @@
+*.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
+Phi-3.5-mini-instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-3.5-mini-instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Phi-3.5-mini-instruct-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c8e68cee3f2c094f4817cf9da33649c957c7ef3d3de8f0f6a1fb708c107925
+size 917107872

Phi-3.5-mini-instruct-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83307e988e48437294d5f2c278f1550cebf5f1e73895239e330875f8c7fc5646
+size 841610400

Phi-3.5-mini-instruct-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d18c5dae68eff4be2af9ebf01f648af528df9e750871b178c0cfbc548feccba
+size 1316395680

Phi-3.5-mini-instruct-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8665c3d3c89053c4e018a8d03a9c57cb95eb87070183bb1a8c58464de57a8878
+size 1215732384

Phi-3.5-mini-instruct-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddca84a79106d2f65c18e901f35c7e837e5ca08dcc176949d4a5fe5d2029456
+size 1153037472

Phi-3.5-mini-instruct-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6baa24866f1eb3b0ab36502db24d73fa14c6ecaecc2a859160e12fe4c14d854
+size 1042936992

Phi-3.5-mini-instruct-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b460de1fba5b009e9fb2fb5458c6d50185db79d393696f2b8987221c5e4fbcf7
+size 1855600800

Phi-3.5-mini-instruct-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f5c42bbd1e9337a881664ee213ea83b4d5cd9e24b7a5ae944224b07fcf2a57
+size 1681799328

Phi-3.5-mini-instruct-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d274c2abc3754b8b4f726debd0d1052c02621754b5eb0b75124e14c855f954ac
+size 1625176224

Phi-3.5-mini-instruct-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17973b87ed4f184993d0b8ab9bcf964ba2287f15a2f1216d1d4171173684f28b
+size 1513003680

Phi-3.5-mini-instruct-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b8e06a17b2d0d7c2c0a99520c2f8498f6ddd5ee8d2d5df848f1236ebf5deb2
+size 2176177824

Phi-3.5-mini-instruct-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846f62dd6d203f6139aa0bba41f8ecc6e3a011b7574c0e60bf9cf06be82266ef
+size 2059853472

Phi-3.5-mini-instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77dc3f12c9ce32fc648ba7d8e64d4903fb3696f3ecb0f6649be306d333b00f96
+size 1416204960

Phi-3.5-mini-instruct-Q2_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f19579dbf551a90ba018650395f10c36c817e159e0a96b62e221fcc584d5560
+size 1327338144

Phi-3.5-mini-instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191155baa511ac50eb7bf763758c8930117e1fc0d949b0d0bba679965a1ec9a1
+size 2087598240

Phi-3.5-mini-instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d9a606dbb12d1093f8510d612c9756c7849003c8ac5afcd8dcc8e61b6f7a31
+size 1955477664

Phi-3.5-mini-instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6364c08f9cf8fb9f8cff255b6c7f2271a90dbcbf92b19b4d8b9969ed7f5da8
+size 1681799328

Phi-3.5-mini-instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1046a58d065e273aa8543078b744d4e675626b6e2682b9f0ecaaa052b8c3cc6d
+size 2182469280

Phi-3.5-mini-instruct-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b0450473116c6cfa36b2a1382c005e0fb2fc741f45d46a239639a3d4a860ab
+size 2408826528

Phi-3.5-mini-instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6882b07ded3a57182faf2e3e6a255d6c6113a6db2d8aebf54275a1c51e6336df
+size 2393233056

Phi-3.5-mini-instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ed82f415606d80b82c244f3fe384ce707751ad9fa5005460b26777cdf6313f
+size 2188760736

Phi-3.5-mini-instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966726cbcd943c077598b7973727857dfb40872acafdeaa939db929e427458f0
+size 2647766688

Phi-3.5-mini-instruct-Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a157996596774f4905ea8a180cc8613989e024f690d7f8e334f3e6d6983cc7
+size 2874123936

Phi-3.5-mini-instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294feeb1733140c9e578410d4c9ec35425f5823c42677d87eedd9778e2f2d6e1
+size 2815276704

Phi-3.5-mini-instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb03d696110775f97ada22d069af9fcd2369ca469f46d604803abf6f2f08ce2
+size 2641475232

Phi-3.5-mini-instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0829fd1fe0d4fa6dbae0723621326973a5df7d2e064a3950c4bacdfdfe6e236a
+size 3135853728

Phi-3.5-mini-instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2a885daeddbaca4398e26b0bdad041fb35b023e487937567f5912cb001d4ab
+size 4061223072

README.md

@@ -0,0 +1,99 @@
+---
+license: other
+language:
+- en
+pipeline_tag: text-generation
+inference: false
+tags:
+- transformers
+- gguf
+- imatrix
+- Phi-3.5-mini-instruct
+---
+Quantizations of https://huggingface.co/microsoft/Phi-3.5-mini-instruct
+
+
+### Inference Clients/UIs
+* [llama.cpp](https://github.com/ggerganov/llama.cpp)
+* [JanAI](https://github.com/janhq/jan)
+* [KoboldCPP](https://github.com/LostRuins/koboldcpp)
+* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
+* [ollama](https://github.com/ollama/ollama)
+* [GPT4All](https://github.com/nomic-ai/gpt4all)
+
+---
+
+# From original readme
+
+Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.
+
+## Usage
+
+### Requirements
+Phi-3 family has been integrated in the `4.43.0` version of `transformers`. The current `transformers` version can be verified with: `pip list | grep transformers`.
+
+Examples of required packages:
+```
+flash_attn==2.5.8
+torch==2.3.1
+accelerate==0.31.0
+transformers==4.43.0
+```
+
+Phi-3.5-mini-instruct is also available in [Azure AI Studio](https://aka.ms/try-phi3.5mini)
+
+### Tokenizer
+
+Phi-3.5-mini-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3.5-mini-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size.
+
+### Input Formats
+Given the nature of the training data, the Phi-3.5-mini-instruct model is best suited for prompts using the chat format as follows:
+
+```
+<|system|>
+You are a helpful assistant.<|end|>
+<|user|>
+How to explain Internet for a medieval knight?<|end|>
+<|assistant|>
+```
+
+### Loading the model locally
+After obtaining the Phi-3.5-mini-instruct model checkpoint, users can use this sample code for inference.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+torch.random.manual_seed(0)
+
+model = AutoModelForCausalLM.from_pretrained(
+    "microsoft/Phi-3.5-mini-instruct", 
+    device_map="cuda", 
+    torch_dtype="auto", 
+    trust_remote_code=True, 
+)
+tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3.5-mini-instruct")
+
+messages = [
+    {"role": "system", "content": "You are a helpful AI assistant."},
+    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
+    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
+    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
+]
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+)
+
+generation_args = {
+    "max_new_tokens": 500,
+    "return_full_text": False,
+    "temperature": 0.0,
+    "do_sample": False,
+}
+
+output = pipe(messages, **generation_args)
+print(output[0]['generated_text'])
+```