Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- MiniChat-1.5-3B-Q2_K.gguf +3 -0
- MiniChat-1.5-3B-Q3_K_L.gguf +3 -0
- MiniChat-1.5-3B-Q3_K_M.gguf +3 -0
- MiniChat-1.5-3B-Q3_K_S.gguf +3 -0
- MiniChat-1.5-3B-Q4_0.gguf +3 -0
- MiniChat-1.5-3B-Q4_K_M.gguf +3 -0
- MiniChat-1.5-3B-Q4_K_S.gguf +3 -0
- MiniChat-1.5-3B-Q5_0.gguf +3 -0
- MiniChat-1.5-3B-Q5_K_M.gguf +3 -0
- MiniChat-1.5-3B-Q5_K_S.gguf +3 -0
- MiniChat-1.5-3B-Q6_K.gguf +3 -0
- MiniChat-1.5-3B-Q8_0.gguf +3 -0
- README.md +185 -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 |
+
MiniChat-1.5-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
MiniChat-1.5-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
MiniChat-1.5-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
MiniChat-1.5-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
MiniChat-1.5-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
MiniChat-1.5-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
MiniChat-1.5-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
MiniChat-1.5-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
MiniChat-1.5-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
MiniChat-1.5-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
MiniChat-1.5-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
MiniChat-1.5-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
MiniChat-1.5-3B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdc7b9ef749f54286d07d1dd44a8544c86d878cf25a23cb76f93d6e614685a6d
|
3 |
+
size 1174505312
|
MiniChat-1.5-3B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9a1acf9007edb3f0e2d83fc6e40d7c1efcbfcab68b1e7667229f0b390fe8775
|
3 |
+
size 1631049056
|
MiniChat-1.5-3B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:942d9e33fe2b999c6b6162144b2c9abb8943b1c4ab9e60457766b037c7937db8
|
3 |
+
size 1504433504
|
MiniChat-1.5-3B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15c70f2fc702b6a6e9f6af18b937e5acbb3cc2c29a14520299c2fb2e9fc222d3
|
3 |
+
size 1358550368
|
MiniChat-1.5-3B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a1bf8332b25e524e2dd527f6d782aa9df83a14c2fcf05cd021b26621b161ee8
|
3 |
+
size 1739602784
|
MiniChat-1.5-3B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e00a42f708684aeebe385da18dc12015b8c92f1c9a020125e8c743008d73b3b
|
3 |
+
size 1846655840
|
MiniChat-1.5-3B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e1f0cb32618e4d46819743ff2cbd5140ad5408ee9c1ee5d80d079d8f995eaba
|
3 |
+
size 1753758560
|
MiniChat-1.5-3B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a92d035ccdb150546071c9a4f9555428550d2ea0f93f8332062e36f8e2b6fbb8
|
3 |
+
size 2098240352
|
MiniChat-1.5-3B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3b7c7dc5237ebbe69ce05d36fab4619f33676fa79b5096d1c743688b8288437
|
3 |
+
size 2153388896
|
MiniChat-1.5-3B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:695df6b1ae59d70be61841bd347a7ffdc7aa5ff5914068ff104841eeb07ef54e
|
3 |
+
size 2098240352
|
MiniChat-1.5-3B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b19329873fb64d44e4febe18f10ff79d6cf7e5ba1231f4bdc0741105274a2716
|
3 |
+
size 2479292768
|
MiniChat-1.5-3B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caeca1eb17386c7f5d653c04213bdd4f60b60ff54602f891f437fde870ac9be4
|
3 |
+
size 3210769760
|
README.md
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- zh
|
5 |
+
license: apache-2.0
|
6 |
+
library_name: transformers
|
7 |
+
widget:
|
8 |
+
- text: <s> [|User|] Hi 👋 </s>[|Assistant|]
|
9 |
+
base_model: GeneZC/MiniChat-1.5-3B
|
10 |
+
tags:
|
11 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
model-index:
|
14 |
+
- name: MiniChat-1.5-3B
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
type: text-generation
|
18 |
+
name: Text Generation
|
19 |
+
dataset:
|
20 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
21 |
+
type: ai2_arc
|
22 |
+
config: ARC-Challenge
|
23 |
+
split: test
|
24 |
+
args:
|
25 |
+
num_few_shot: 25
|
26 |
+
metrics:
|
27 |
+
- type: acc_norm
|
28 |
+
value: 46.5
|
29 |
+
name: normalized accuracy
|
30 |
+
source:
|
31 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
|
32 |
+
name: Open LLM Leaderboard
|
33 |
+
- task:
|
34 |
+
type: text-generation
|
35 |
+
name: Text Generation
|
36 |
+
dataset:
|
37 |
+
name: HellaSwag (10-Shot)
|
38 |
+
type: hellaswag
|
39 |
+
split: validation
|
40 |
+
args:
|
41 |
+
num_few_shot: 10
|
42 |
+
metrics:
|
43 |
+
- type: acc_norm
|
44 |
+
value: 68.28
|
45 |
+
name: normalized accuracy
|
46 |
+
source:
|
47 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
|
48 |
+
name: Open LLM Leaderboard
|
49 |
+
- task:
|
50 |
+
type: text-generation
|
51 |
+
name: Text Generation
|
52 |
+
dataset:
|
53 |
+
name: MMLU (5-Shot)
|
54 |
+
type: cais/mmlu
|
55 |
+
config: all
|
56 |
+
split: test
|
57 |
+
args:
|
58 |
+
num_few_shot: 5
|
59 |
+
metrics:
|
60 |
+
- type: acc
|
61 |
+
value: 46.67
|
62 |
+
name: accuracy
|
63 |
+
source:
|
64 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
|
65 |
+
name: Open LLM Leaderboard
|
66 |
+
- task:
|
67 |
+
type: text-generation
|
68 |
+
name: Text Generation
|
69 |
+
dataset:
|
70 |
+
name: TruthfulQA (0-shot)
|
71 |
+
type: truthful_qa
|
72 |
+
config: multiple_choice
|
73 |
+
split: validation
|
74 |
+
args:
|
75 |
+
num_few_shot: 0
|
76 |
+
metrics:
|
77 |
+
- type: mc2
|
78 |
+
value: 50.71
|
79 |
+
source:
|
80 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
|
81 |
+
name: Open LLM Leaderboard
|
82 |
+
- task:
|
83 |
+
type: text-generation
|
84 |
+
name: Text Generation
|
85 |
+
dataset:
|
86 |
+
name: Winogrande (5-shot)
|
87 |
+
type: winogrande
|
88 |
+
config: winogrande_xl
|
89 |
+
split: validation
|
90 |
+
args:
|
91 |
+
num_few_shot: 5
|
92 |
+
metrics:
|
93 |
+
- type: acc
|
94 |
+
value: 65.04
|
95 |
+
name: accuracy
|
96 |
+
source:
|
97 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
|
98 |
+
name: Open LLM Leaderboard
|
99 |
+
- task:
|
100 |
+
type: text-generation
|
101 |
+
name: Text Generation
|
102 |
+
dataset:
|
103 |
+
name: GSM8k (5-shot)
|
104 |
+
type: gsm8k
|
105 |
+
config: main
|
106 |
+
split: test
|
107 |
+
args:
|
108 |
+
num_few_shot: 5
|
109 |
+
metrics:
|
110 |
+
- type: acc
|
111 |
+
value: 24.18
|
112 |
+
name: accuracy
|
113 |
+
source:
|
114 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=GeneZC/MiniChat-1.5-3B
|
115 |
+
name: Open LLM Leaderboard
|
116 |
+
---
|
117 |
+
|
118 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
119 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
120 |
+
</div>
|
121 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
122 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
123 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
124 |
+
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>
|
125 |
+
</p>
|
126 |
+
</div>
|
127 |
+
</div>
|
128 |
+
|
129 |
+
## GeneZC/MiniChat-1.5-3B - GGUF
|
130 |
+
|
131 |
+
This repo contains GGUF format model files for [GeneZC/MiniChat-1.5-3B](https://huggingface.co/GeneZC/MiniChat-1.5-3B).
|
132 |
+
|
133 |
+
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).
|
134 |
+
|
135 |
+
<div style="text-align: left; margin: 20px 0;">
|
136 |
+
<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;">
|
137 |
+
Run them on the TensorBlock client using your local machine ↗
|
138 |
+
</a>
|
139 |
+
</div>
|
140 |
+
|
141 |
+
## Prompt template
|
142 |
+
|
143 |
+
```
|
144 |
+
‘MiniChat’是一个由‘Beccurio’开发的AI语言模型。下面是人类和MiniChat之间的一段对话。MiniChat的回复应当尽可能详细,并且以Markdown的形式输出。MiniChat应当拒绝参与违背伦理的讨论。</s>[|System|] {system_prompt}</s>[|User|] {prompt}</s>[|Assistant|]
|
145 |
+
```
|
146 |
+
|
147 |
+
## Model file specification
|
148 |
+
|
149 |
+
| Filename | Quant type | File Size | Description |
|
150 |
+
| -------- | ---------- | --------- | ----------- |
|
151 |
+
| [MiniChat-1.5-3B-Q2_K.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q2_K.gguf) | Q2_K | 1.094 GB | smallest, significant quality loss - not recommended for most purposes |
|
152 |
+
| [MiniChat-1.5-3B-Q3_K_S.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q3_K_S.gguf) | Q3_K_S | 1.265 GB | very small, high quality loss |
|
153 |
+
| [MiniChat-1.5-3B-Q3_K_M.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q3_K_M.gguf) | Q3_K_M | 1.401 GB | very small, high quality loss |
|
154 |
+
| [MiniChat-1.5-3B-Q3_K_L.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q3_K_L.gguf) | Q3_K_L | 1.519 GB | small, substantial quality loss |
|
155 |
+
| [MiniChat-1.5-3B-Q4_0.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q4_0.gguf) | Q4_0 | 1.620 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
156 |
+
| [MiniChat-1.5-3B-Q4_K_S.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q4_K_S.gguf) | Q4_K_S | 1.633 GB | small, greater quality loss |
|
157 |
+
| [MiniChat-1.5-3B-Q4_K_M.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q4_K_M.gguf) | Q4_K_M | 1.720 GB | medium, balanced quality - recommended |
|
158 |
+
| [MiniChat-1.5-3B-Q5_0.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q5_0.gguf) | Q5_0 | 1.954 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
159 |
+
| [MiniChat-1.5-3B-Q5_K_S.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q5_K_S.gguf) | Q5_K_S | 1.954 GB | large, low quality loss - recommended |
|
160 |
+
| [MiniChat-1.5-3B-Q5_K_M.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q5_K_M.gguf) | Q5_K_M | 2.005 GB | large, very low quality loss - recommended |
|
161 |
+
| [MiniChat-1.5-3B-Q6_K.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q6_K.gguf) | Q6_K | 2.309 GB | very large, extremely low quality loss |
|
162 |
+
| [MiniChat-1.5-3B-Q8_0.gguf](https://huggingface.co/tensorblock/MiniChat-1.5-3B-GGUF/blob/main/MiniChat-1.5-3B-Q8_0.gguf) | Q8_0 | 2.990 GB | very large, extremely low quality loss - not recommended |
|
163 |
+
|
164 |
+
|
165 |
+
## Downloading instruction
|
166 |
+
|
167 |
+
### Command line
|
168 |
+
|
169 |
+
Firstly, install Huggingface Client
|
170 |
+
|
171 |
+
```shell
|
172 |
+
pip install -U "huggingface_hub[cli]"
|
173 |
+
```
|
174 |
+
|
175 |
+
Then, downoad the individual model file the a local directory
|
176 |
+
|
177 |
+
```shell
|
178 |
+
huggingface-cli download tensorblock/MiniChat-1.5-3B-GGUF --include "MiniChat-1.5-3B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
179 |
+
```
|
180 |
+
|
181 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
182 |
+
|
183 |
+
```shell
|
184 |
+
huggingface-cli download tensorblock/MiniChat-1.5-3B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
185 |
+
```
|