Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,9 @@
-*.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
+Mixtral_7Bx5_MoE_30B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Mixtral_7Bx5_MoE_30B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Mixtral_7Bx5_MoE_30B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85fcfae8644f132cb3abd4963b3a11f09ab3ab6d8eda12baf24188aa6adef4dd
+size 15449972384

Mixtral_7Bx5_MoE_30B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c33a0231525e53f7c29943bed49d8cd509f47ec8e0e36ec54b9b4476eea7672
+size 14266130080

Mixtral_7Bx5_MoE_30B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c47923f52d41bc39de7659609e4f97827fbe09615d3a3a0e13d61369d17ea0
+size 12854746784

Mixtral_7Bx5_MoE_30B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4a9e512db5d76606dc493a19d371a0b829e698e481fee2a3eb635732eb7eaf
+size 18022235808

Mixtral_7Bx5_MoE_30B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16aa649e3b369b6b8d1320a246a5bbbc6ccea4712d513ddf758192e2d2650802
+size 16942726816

Mixtral_7Bx5_MoE_30B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1558080dc19db67c8e6cef6fa0063438f45419c4d01fbfdc4cff5bccb0359b4
+size 21134016160

Mixtral_7Bx5_MoE_30B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e04577c0ba55eee1d1ab9a9d5ad8b25d12099f74e438461b5c0523cfd97b544
+size 20501200544

Mixtral_7Bx5_MoE_30B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35896fa06d17244ec0e6a16685bfafe3739d2e76b59b1a15b20ada3224569d5
+size 24440282784

Mixtral_7Bx5_MoE_30B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c698e5578ae5d00af934d7196b5ada5beab7dbdc168ffb6fd671a8114a0f9811
+size 31655059104

README.md

@@ -0,0 +1,67 @@
+---
+  license: cc-by-nc-4.0
+---
+
+# Mixtral MOE 5x7B
+
+MoE  of the following models :
+
+* [Toten5/Marcoroni-neural-chat-7B-v1](https://huggingface.co/Toten5/Marcoroni-neural-chat-7B-v1)
+* [NurtureAI/neural-chat-7b-v3-16k](https://huggingface.co/NurtureAI/neural-chat-7b-v3-16k)
+* [mncai/mistral-7b-dpo-v6](https://huggingface.co/mncai/mistral-7b-dpo-v6)
+* [cookinai/CatMacaroni-Slerp](https://huggingface.co/cookinai/CatMacaroni-Slerp)
+* [ignos/Mistral-T5-7B-v1](https://huggingface.co/ignos/Mistral-T5-7B-v1)
+
+
+gpu code example
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+## v2 models
+model_path = "cloudyu/Mixtral_7Bx5_MoE_30B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
+
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")
+```
+
+CPU example
+
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+## v2 models
+model_path = "cloudyu/Mixtral_7Bx5_MoE_30B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.float32, device_map='cpu',local_files_only=False
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")
+
+```