Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- MixTAO-7Bx2-MoE-v8.1-Q2_K.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q3_K_L.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q3_K_M.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q3_K_S.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q4_0.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q4_K_M.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q4_K_S.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q5_0.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q5_K_M.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q5_K_S.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q6_K.gguf +3 -0
- MixTAO-7Bx2-MoE-v8.1-Q8_0.gguf +3 -0
- README.md +178 -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 |
+
MixTAO-7Bx2-MoE-v8.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
MixTAO-7Bx2-MoE-v8.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
MixTAO-7Bx2-MoE-v8.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
MixTAO-7Bx2-MoE-v8.1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
MixTAO-7Bx2-MoE-v8.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
MixTAO-7Bx2-MoE-v8.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
MixTAO-7Bx2-MoE-v8.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
MixTAO-7Bx2-MoE-v8.1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
MixTAO-7Bx2-MoE-v8.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
MixTAO-7Bx2-MoE-v8.1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
MixTAO-7Bx2-MoE-v8.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
MixTAO-7Bx2-MoE-v8.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
MixTAO-7Bx2-MoE-v8.1-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26b4112cbf1dfb74e0e8cafee3cf9ef68c3df817c4fda9ffc12e1b4cb4fc5953
|
3 |
+
size 4760823776
|
MixTAO-7Bx2-MoE-v8.1-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20762669a39348917278ee4f4a66a2942fee8e401affcd89e0b109b7114e5e90
|
3 |
+
size 6729730016
|
MixTAO-7Bx2-MoE-v8.1-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3176d037f78f03deebfeec530de05cbc67633cfd42c99b838ded305043c4867
|
3 |
+
size 6206490592
|
MixTAO-7Bx2-MoE-v8.1-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85c586262c4063ac8ade317152af1341055114b9e028038bfcdb7675569ce0de
|
3 |
+
size 5587830752
|
MixTAO-7Bx2-MoE-v8.1-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09f9624e0216984348c5ce2970e081c4af7aea5fb9084248500e0c27c405f616
|
3 |
+
size 7280863200
|
MixTAO-7Bx2-MoE-v8.1-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0508780b50fef9e4bc24c01fde65f19fef1d68ae3fbedc60a7b1645aa5f9e479
|
3 |
+
size 7782606816
|
MixTAO-7Bx2-MoE-v8.1-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e34441a6d383401a80ddfa1c9edcd721e5b61247c315af2dacc8dd829f86a4f
|
3 |
+
size 7341680608
|
MixTAO-7Bx2-MoE-v8.1-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1967fca247acede7aa1e94123617f705ebce52c1a9fce6281db82b026d373613
|
3 |
+
size 8874305504
|
MixTAO-7Bx2-MoE-v8.1-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d24ad530b8fe5a386f67cbc41a4efbf2b80ef5c67aa5ad7bd2fef37befbba85
|
3 |
+
size 9132779488
|
MixTAO-7Bx2-MoE-v8.1-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4c0c3a7b1dfd3374565b8178cba17e03621aabe8dad927877661c5e4ebfcc44
|
3 |
+
size 8874305504
|
MixTAO-7Bx2-MoE-v8.1-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:560766932ae588e4dc9e4193615fad3e65f8432aa6aa5f01e0c0198da7d5f977
|
3 |
+
size 10567337952
|
MixTAO-7Bx2-MoE-v8.1-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e92f63bd0f23cfa033ec28120381b0a99deaf2eef18263e6f8b234e43c1351d9
|
3 |
+
size 13686376416
|
README.md
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- TensorBlock
|
6 |
+
- GGUF
|
7 |
+
base_model: mixtao/MixTAO-7Bx2-MoE-v8.1
|
8 |
+
model-index:
|
9 |
+
- name: MixTAO-7Bx2-MoE-v8.1
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: text-generation
|
13 |
+
name: Text Generation
|
14 |
+
dataset:
|
15 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
16 |
+
type: ai2_arc
|
17 |
+
config: ARC-Challenge
|
18 |
+
split: test
|
19 |
+
args:
|
20 |
+
num_few_shot: 25
|
21 |
+
metrics:
|
22 |
+
- type: acc_norm
|
23 |
+
value: 73.81
|
24 |
+
name: normalized accuracy
|
25 |
+
source:
|
26 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
|
27 |
+
name: Open LLM Leaderboard
|
28 |
+
- task:
|
29 |
+
type: text-generation
|
30 |
+
name: Text Generation
|
31 |
+
dataset:
|
32 |
+
name: HellaSwag (10-Shot)
|
33 |
+
type: hellaswag
|
34 |
+
split: validation
|
35 |
+
args:
|
36 |
+
num_few_shot: 10
|
37 |
+
metrics:
|
38 |
+
- type: acc_norm
|
39 |
+
value: 89.22
|
40 |
+
name: normalized accuracy
|
41 |
+
source:
|
42 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
|
43 |
+
name: Open LLM Leaderboard
|
44 |
+
- task:
|
45 |
+
type: text-generation
|
46 |
+
name: Text Generation
|
47 |
+
dataset:
|
48 |
+
name: MMLU (5-Shot)
|
49 |
+
type: cais/mmlu
|
50 |
+
config: all
|
51 |
+
split: test
|
52 |
+
args:
|
53 |
+
num_few_shot: 5
|
54 |
+
metrics:
|
55 |
+
- type: acc
|
56 |
+
value: 64.92
|
57 |
+
name: accuracy
|
58 |
+
source:
|
59 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
|
60 |
+
name: Open LLM Leaderboard
|
61 |
+
- task:
|
62 |
+
type: text-generation
|
63 |
+
name: Text Generation
|
64 |
+
dataset:
|
65 |
+
name: TruthfulQA (0-shot)
|
66 |
+
type: truthful_qa
|
67 |
+
config: multiple_choice
|
68 |
+
split: validation
|
69 |
+
args:
|
70 |
+
num_few_shot: 0
|
71 |
+
metrics:
|
72 |
+
- type: mc2
|
73 |
+
value: 78.57
|
74 |
+
source:
|
75 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
|
76 |
+
name: Open LLM Leaderboard
|
77 |
+
- task:
|
78 |
+
type: text-generation
|
79 |
+
name: Text Generation
|
80 |
+
dataset:
|
81 |
+
name: Winogrande (5-shot)
|
82 |
+
type: winogrande
|
83 |
+
config: winogrande_xl
|
84 |
+
split: validation
|
85 |
+
args:
|
86 |
+
num_few_shot: 5
|
87 |
+
metrics:
|
88 |
+
- type: acc
|
89 |
+
value: 87.37
|
90 |
+
name: accuracy
|
91 |
+
source:
|
92 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
|
93 |
+
name: Open LLM Leaderboard
|
94 |
+
- task:
|
95 |
+
type: text-generation
|
96 |
+
name: Text Generation
|
97 |
+
dataset:
|
98 |
+
name: GSM8k (5-shot)
|
99 |
+
type: gsm8k
|
100 |
+
config: main
|
101 |
+
split: test
|
102 |
+
args:
|
103 |
+
num_few_shot: 5
|
104 |
+
metrics:
|
105 |
+
- type: acc
|
106 |
+
value: 71.11
|
107 |
+
name: accuracy
|
108 |
+
source:
|
109 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=zhengr/MixTAO-7Bx2-MoE-v8.1
|
110 |
+
name: Open LLM Leaderboard
|
111 |
+
---
|
112 |
+
|
113 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
114 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
115 |
+
</div>
|
116 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
117 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
118 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
119 |
+
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>
|
120 |
+
</p>
|
121 |
+
</div>
|
122 |
+
</div>
|
123 |
+
|
124 |
+
## mixtao/MixTAO-7Bx2-MoE-v8.1 - GGUF
|
125 |
+
|
126 |
+
This repo contains GGUF format model files for [mixtao/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/mixtao/MixTAO-7Bx2-MoE-v8.1).
|
127 |
+
|
128 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
129 |
+
|
130 |
+
## Prompt template
|
131 |
+
|
132 |
+
```
|
133 |
+
### System:
|
134 |
+
{system_prompt}
|
135 |
+
### Instruction:
|
136 |
+
{prompt}
|
137 |
+
### Response:
|
138 |
+
```
|
139 |
+
|
140 |
+
## Model file specification
|
141 |
+
|
142 |
+
| Filename | Quant type | File Size | Description |
|
143 |
+
| -------- | ---------- | --------- | ----------- |
|
144 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q2_K.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q2_K.gguf) | Q2_K | 4.434 GB | smallest, significant quality loss - not recommended for most purposes |
|
145 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q3_K_S.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q3_K_S.gguf) | Q3_K_S | 5.204 GB | very small, high quality loss |
|
146 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q3_K_M.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q3_K_M.gguf) | Q3_K_M | 5.780 GB | very small, high quality loss |
|
147 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q3_K_L.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q3_K_L.gguf) | Q3_K_L | 6.268 GB | small, substantial quality loss |
|
148 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q4_0.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q4_0.gguf) | Q4_0 | 6.781 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
149 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q4_K_S.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q4_K_S.gguf) | Q4_K_S | 6.837 GB | small, greater quality loss |
|
150 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q4_K_M.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q4_K_M.gguf) | Q4_K_M | 7.248 GB | medium, balanced quality - recommended |
|
151 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q5_0.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q5_0.gguf) | Q5_0 | 8.265 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
152 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q5_K_S.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q5_K_S.gguf) | Q5_K_S | 8.265 GB | large, low quality loss - recommended |
|
153 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q5_K_M.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q5_K_M.gguf) | Q5_K_M | 8.506 GB | large, very low quality loss - recommended |
|
154 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q6_K.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q6_K.gguf) | Q6_K | 9.842 GB | very large, extremely low quality loss |
|
155 |
+
| [MixTAO-7Bx2-MoE-v8.1-Q8_0.gguf](https://huggingface.co/tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF/tree/main/MixTAO-7Bx2-MoE-v8.1-Q8_0.gguf) | Q8_0 | 12.746 GB | very large, extremely low quality loss - not recommended |
|
156 |
+
|
157 |
+
|
158 |
+
## Downloading instruction
|
159 |
+
|
160 |
+
### Command line
|
161 |
+
|
162 |
+
Firstly, install Huggingface Client
|
163 |
+
|
164 |
+
```shell
|
165 |
+
pip install -U "huggingface_hub[cli]"
|
166 |
+
```
|
167 |
+
|
168 |
+
Then, downoad the individual model file the a local directory
|
169 |
+
|
170 |
+
```shell
|
171 |
+
huggingface-cli download tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF --include "MixTAO-7Bx2-MoE-v8.1-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
172 |
+
```
|
173 |
+
|
174 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
175 |
+
|
176 |
+
```shell
|
177 |
+
huggingface-cli download tensorblock/MixTAO-7Bx2-MoE-v8.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
178 |
+
```
|