Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_L.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_M.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_S.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q4_0.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_M.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_S.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q5_0.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_M.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_S.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q6_K.gguf +3 -0
- Mixtral-8x7B-Instruct-v0.1-DPO-Q8_0.gguf +3 -0
- README.md +186 -0
.gitattributes
CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Mixtral-8x7B-Instruct-v0.1-DPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c447abc4546755e502a40a4080395a4a262c23d0a8b2fc9f1edd8b6f7cd56b67
|
3 |
+
size 17311230016
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82b0a28ce595814b8247bb9861585b2d5e0caf0fa12abd8cd6c99ef5de5ea343
|
3 |
+
size 24169646144
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38c835df099ea40eabf949146ede8ce859256ad827cad56f97a997ae26d77327
|
3 |
+
size 22546450496
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0c967be8824192eadb8b336e745750a7f12d680b0d6ab0851fa2b475b43b981
|
3 |
+
size 20432521280
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08d9a14202175d1cfc8108b1818900f55870717a7b2de3d5c3ae655f09282d3d
|
3 |
+
size 26443589696
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ba8de4e2b1aa9a181b95de2aac3cb90364b983f7632469049aa0fa58d893685
|
3 |
+
size 28448467008
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:675976fe810a82611feb9188fbfa915d29923c748668b3a0f5f88658ecd62f8b
|
3 |
+
size 26745579584
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02fc8d00cf44adbc6812308a16b788c8ebb923010d1503439e8f91f42ec5d52c
|
3 |
+
size 32231336000
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27116a5ad4aa9df2e0a6fedfe7dbaa0651c94756b7a6d2dcc0ae18ed483c216b
|
3 |
+
size 33229580352
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:699ef92233b115deadce10c77324a50fda16df63ca6cc4af78132d84d6411ea8
|
3 |
+
size 32231336000
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73f16924da926adb4549b5e96d6af5177a393d4049117a537bddca40f9aa82b
|
3 |
+
size 38380816448
|
Mixtral-8x7B-Instruct-v0.1-DPO-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb400de292d5c6c593ad10384376754c8918b5b02669621e257086ee3fc11a86
|
3 |
+
size 49626318912
|
README.md
ADDED
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- fr
|
4 |
+
- it
|
5 |
+
- de
|
6 |
+
- es
|
7 |
+
- en
|
8 |
+
license: apache-2.0
|
9 |
+
tags:
|
10 |
+
- moe
|
11 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
base_model: cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
|
14 |
+
model-index:
|
15 |
+
- name: Mixtral-8x7B-Instruct-v0.1-DPO
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
type: text-generation
|
19 |
+
name: Text Generation
|
20 |
+
dataset:
|
21 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
22 |
+
type: ai2_arc
|
23 |
+
config: ARC-Challenge
|
24 |
+
split: test
|
25 |
+
args:
|
26 |
+
num_few_shot: 25
|
27 |
+
metrics:
|
28 |
+
- type: acc_norm
|
29 |
+
value: 69.8
|
30 |
+
name: normalized accuracy
|
31 |
+
source:
|
32 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
|
33 |
+
name: Open LLM Leaderboard
|
34 |
+
- task:
|
35 |
+
type: text-generation
|
36 |
+
name: Text Generation
|
37 |
+
dataset:
|
38 |
+
name: HellaSwag (10-Shot)
|
39 |
+
type: hellaswag
|
40 |
+
split: validation
|
41 |
+
args:
|
42 |
+
num_few_shot: 10
|
43 |
+
metrics:
|
44 |
+
- type: acc_norm
|
45 |
+
value: 87.83
|
46 |
+
name: normalized accuracy
|
47 |
+
source:
|
48 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
|
49 |
+
name: Open LLM Leaderboard
|
50 |
+
- task:
|
51 |
+
type: text-generation
|
52 |
+
name: Text Generation
|
53 |
+
dataset:
|
54 |
+
name: MMLU (5-Shot)
|
55 |
+
type: cais/mmlu
|
56 |
+
config: all
|
57 |
+
split: test
|
58 |
+
args:
|
59 |
+
num_few_shot: 5
|
60 |
+
metrics:
|
61 |
+
- type: acc
|
62 |
+
value: 71.05
|
63 |
+
name: accuracy
|
64 |
+
source:
|
65 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
|
66 |
+
name: Open LLM Leaderboard
|
67 |
+
- task:
|
68 |
+
type: text-generation
|
69 |
+
name: Text Generation
|
70 |
+
dataset:
|
71 |
+
name: TruthfulQA (0-shot)
|
72 |
+
type: truthful_qa
|
73 |
+
config: multiple_choice
|
74 |
+
split: validation
|
75 |
+
args:
|
76 |
+
num_few_shot: 0
|
77 |
+
metrics:
|
78 |
+
- type: mc2
|
79 |
+
value: 69.18
|
80 |
+
source:
|
81 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
|
82 |
+
name: Open LLM Leaderboard
|
83 |
+
- task:
|
84 |
+
type: text-generation
|
85 |
+
name: Text Generation
|
86 |
+
dataset:
|
87 |
+
name: Winogrande (5-shot)
|
88 |
+
type: winogrande
|
89 |
+
config: winogrande_xl
|
90 |
+
split: validation
|
91 |
+
args:
|
92 |
+
num_few_shot: 5
|
93 |
+
metrics:
|
94 |
+
- type: acc
|
95 |
+
value: 81.37
|
96 |
+
name: accuracy
|
97 |
+
source:
|
98 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
|
99 |
+
name: Open LLM Leaderboard
|
100 |
+
- task:
|
101 |
+
type: text-generation
|
102 |
+
name: Text Generation
|
103 |
+
dataset:
|
104 |
+
name: GSM8k (5-shot)
|
105 |
+
type: gsm8k
|
106 |
+
config: main
|
107 |
+
split: test
|
108 |
+
args:
|
109 |
+
num_few_shot: 5
|
110 |
+
metrics:
|
111 |
+
- type: acc
|
112 |
+
value: 61.41
|
113 |
+
name: accuracy
|
114 |
+
source:
|
115 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO
|
116 |
+
name: Open LLM Leaderboard
|
117 |
+
---
|
118 |
+
|
119 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
120 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
121 |
+
</div>
|
122 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
123 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
124 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
125 |
+
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
|
126 |
+
</p>
|
127 |
+
</div>
|
128 |
+
</div>
|
129 |
+
|
130 |
+
## cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO - GGUF
|
131 |
+
|
132 |
+
This repo contains GGUF format model files for [cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO](https://huggingface.co/cloudyu/Mixtral-8x7B-Instruct-v0.1-DPO).
|
133 |
+
|
134 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
135 |
+
|
136 |
+
<div style="text-align: left; margin: 20px 0;">
|
137 |
+
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
|
138 |
+
Run them on the TensorBlock client using your local machine ↗
|
139 |
+
</a>
|
140 |
+
</div>
|
141 |
+
|
142 |
+
## Prompt template
|
143 |
+
|
144 |
+
```
|
145 |
+
<s>[INST] {prompt} [/INST]
|
146 |
+
```
|
147 |
+
|
148 |
+
## Model file specification
|
149 |
+
|
150 |
+
| Filename | Quant type | File Size | Description |
|
151 |
+
| -------- | ---------- | --------- | ----------- |
|
152 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf) | Q2_K | 17.311 GB | smallest, significant quality loss - not recommended for most purposes |
|
153 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_S.gguf) | Q3_K_S | 20.433 GB | very small, high quality loss |
|
154 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_M.gguf) | Q3_K_M | 22.546 GB | very small, high quality loss |
|
155 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q3_K_L.gguf) | Q3_K_L | 24.170 GB | small, substantial quality loss |
|
156 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q4_0.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q4_0.gguf) | Q4_0 | 26.444 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
157 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_S.gguf) | Q4_K_S | 26.746 GB | small, greater quality loss |
|
158 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q4_K_M.gguf) | Q4_K_M | 28.448 GB | medium, balanced quality - recommended |
|
159 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q5_0.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q5_0.gguf) | Q5_0 | 32.231 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
160 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_S.gguf) | Q5_K_S | 32.231 GB | large, low quality loss - recommended |
|
161 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q5_K_M.gguf) | Q5_K_M | 33.230 GB | large, very low quality loss - recommended |
|
162 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q6_K.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q6_K.gguf) | Q6_K | 38.381 GB | very large, extremely low quality loss |
|
163 |
+
| [Mixtral-8x7B-Instruct-v0.1-DPO-Q8_0.gguf](https://huggingface.co/tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF/blob/main/Mixtral-8x7B-Instruct-v0.1-DPO-Q8_0.gguf) | Q8_0 | 49.626 GB | very large, extremely low quality loss - not recommended |
|
164 |
+
|
165 |
+
|
166 |
+
## Downloading instruction
|
167 |
+
|
168 |
+
### Command line
|
169 |
+
|
170 |
+
Firstly, install Huggingface Client
|
171 |
+
|
172 |
+
```shell
|
173 |
+
pip install -U "huggingface_hub[cli]"
|
174 |
+
```
|
175 |
+
|
176 |
+
Then, downoad the individual model file the a local directory
|
177 |
+
|
178 |
+
```shell
|
179 |
+
huggingface-cli download tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF --include "Mixtral-8x7B-Instruct-v0.1-DPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
180 |
+
```
|
181 |
+
|
182 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
183 |
+
|
184 |
+
```shell
|
185 |
+
huggingface-cli download tensorblock/Mixtral-8x7B-Instruct-v0.1-DPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
186 |
+
```
|