Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Gemmalpaca-2B-Q2_K.gguf +3 -0
- Gemmalpaca-2B-Q3_K_L.gguf +3 -0
- Gemmalpaca-2B-Q3_K_M.gguf +3 -0
- Gemmalpaca-2B-Q3_K_S.gguf +3 -0
- Gemmalpaca-2B-Q4_0.gguf +3 -0
- Gemmalpaca-2B-Q4_K_M.gguf +3 -0
- Gemmalpaca-2B-Q4_K_S.gguf +3 -0
- Gemmalpaca-2B-Q5_0.gguf +3 -0
- Gemmalpaca-2B-Q5_K_M.gguf +3 -0
- Gemmalpaca-2B-Q5_K_S.gguf +3 -0
- Gemmalpaca-2B-Q6_K.gguf +3 -0
- Gemmalpaca-2B-Q8_0.gguf +3 -0
- README.md +189 -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 |
+
Gemmalpaca-2B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Gemmalpaca-2B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Gemmalpaca-2B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Gemmalpaca-2B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Gemmalpaca-2B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Gemmalpaca-2B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Gemmalpaca-2B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Gemmalpaca-2B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Gemmalpaca-2B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Gemmalpaca-2B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Gemmalpaca-2B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Gemmalpaca-2B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Gemmalpaca-2B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:789c7526b03189d147465c901165991ebb441bb4c1b8930a114b901fd456b0c4
|
3 |
+
size 1157924896
|
Gemmalpaca-2B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b7f3bd305b1e5fbf4ddd6d6fb49ce9fe2d85ec8373a1360d24dd51a502d0351
|
3 |
+
size 1465591840
|
Gemmalpaca-2B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caf15e11a180edd244b6e9094e6bccfd3ee68ad965fa55bb1a55ca03a03aa299
|
3 |
+
size 1383802912
|
Gemmalpaca-2B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a596a05cc6c3f7bc5cfaecbbe00d8b08237fa2f7752b0c107e3e4ae780cd9e08
|
3 |
+
size 1287981088
|
Gemmalpaca-2B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:671b1167a8369ad131c5c8f10fb5eefc9189fbe1b80a34fad0f5bd78c3c006a6
|
3 |
+
size 1551190048
|
Gemmalpaca-2B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c736ec195541c38886b85fa9a217af2b7154d096f8c4a492a5a3097ba03f90bc
|
3 |
+
size 1630263328
|
Gemmalpaca-2B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30a48935c018da3521dda66f102d6fd85173eef4bfce2a773ed96ff87c3b0cef
|
3 |
+
size 1559840800
|
Gemmalpaca-2B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecf378ba4d6926c2542a63927bf612829a5a1d6b8bf5050118709695b2965ad3
|
3 |
+
size 1798916128
|
Gemmalpaca-2B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85739adbbc80a9684648780d2530f56aa745291c73353e254c12f8c788da7c68
|
3 |
+
size 1839650848
|
Gemmalpaca-2B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a84facaf70d157593da9d00fd48f4a0be2643c7cf53945244d6b28693310270
|
3 |
+
size 1798916128
|
Gemmalpaca-2B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c98f2f413b74230df77bc98aced070ec5057f25f13108e1ff2d2873a0a8496b0
|
3 |
+
size 2062125088
|
Gemmalpaca-2B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0acc00238a133a2f589edfa70bd2234c2a146f4e412a0fa2d784bee57831d363
|
3 |
+
size 2669070368
|
README.md
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: transformers
|
4 |
+
datasets:
|
5 |
+
- vicgalle/alpaca-gpt4
|
6 |
+
extra_gated_heading: Access Gemma on Hugging Face
|
7 |
+
extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
|
8 |
+
agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
|
9 |
+
Face and click below. Requests are processed immediately.
|
10 |
+
extra_gated_button_content: Acknowledge license
|
11 |
+
license_name: gemma-terms-of-use
|
12 |
+
license_link: https://ai.google.dev/gemma/terms
|
13 |
+
base_model: mlabonne/Gemmalpaca-2B
|
14 |
+
tags:
|
15 |
+
- TensorBlock
|
16 |
+
- GGUF
|
17 |
+
model-index:
|
18 |
+
- name: Gemmalpaca-2B
|
19 |
+
results:
|
20 |
+
- task:
|
21 |
+
type: text-generation
|
22 |
+
name: Text Generation
|
23 |
+
dataset:
|
24 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
25 |
+
type: ai2_arc
|
26 |
+
config: ARC-Challenge
|
27 |
+
split: test
|
28 |
+
args:
|
29 |
+
num_few_shot: 25
|
30 |
+
metrics:
|
31 |
+
- type: acc_norm
|
32 |
+
value: 48.72
|
33 |
+
name: normalized accuracy
|
34 |
+
source:
|
35 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Gemmalpaca-2B
|
36 |
+
name: Open LLM Leaderboard
|
37 |
+
- task:
|
38 |
+
type: text-generation
|
39 |
+
name: Text Generation
|
40 |
+
dataset:
|
41 |
+
name: HellaSwag (10-Shot)
|
42 |
+
type: hellaswag
|
43 |
+
split: validation
|
44 |
+
args:
|
45 |
+
num_few_shot: 10
|
46 |
+
metrics:
|
47 |
+
- type: acc_norm
|
48 |
+
value: 71.36
|
49 |
+
name: normalized accuracy
|
50 |
+
source:
|
51 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Gemmalpaca-2B
|
52 |
+
name: Open LLM Leaderboard
|
53 |
+
- task:
|
54 |
+
type: text-generation
|
55 |
+
name: Text Generation
|
56 |
+
dataset:
|
57 |
+
name: MMLU (5-Shot)
|
58 |
+
type: cais/mmlu
|
59 |
+
config: all
|
60 |
+
split: test
|
61 |
+
args:
|
62 |
+
num_few_shot: 5
|
63 |
+
metrics:
|
64 |
+
- type: acc
|
65 |
+
value: 36.3
|
66 |
+
name: accuracy
|
67 |
+
source:
|
68 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Gemmalpaca-2B
|
69 |
+
name: Open LLM Leaderboard
|
70 |
+
- task:
|
71 |
+
type: text-generation
|
72 |
+
name: Text Generation
|
73 |
+
dataset:
|
74 |
+
name: TruthfulQA (0-shot)
|
75 |
+
type: truthful_qa
|
76 |
+
config: multiple_choice
|
77 |
+
split: validation
|
78 |
+
args:
|
79 |
+
num_few_shot: 0
|
80 |
+
metrics:
|
81 |
+
- type: mc2
|
82 |
+
value: 41.24
|
83 |
+
source:
|
84 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Gemmalpaca-2B
|
85 |
+
name: Open LLM Leaderboard
|
86 |
+
- task:
|
87 |
+
type: text-generation
|
88 |
+
name: Text Generation
|
89 |
+
dataset:
|
90 |
+
name: Winogrande (5-shot)
|
91 |
+
type: winogrande
|
92 |
+
config: winogrande_xl
|
93 |
+
split: validation
|
94 |
+
args:
|
95 |
+
num_few_shot: 5
|
96 |
+
metrics:
|
97 |
+
- type: acc
|
98 |
+
value: 65.59
|
99 |
+
name: accuracy
|
100 |
+
source:
|
101 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Gemmalpaca-2B
|
102 |
+
name: Open LLM Leaderboard
|
103 |
+
- task:
|
104 |
+
type: text-generation
|
105 |
+
name: Text Generation
|
106 |
+
dataset:
|
107 |
+
name: GSM8k (5-shot)
|
108 |
+
type: gsm8k
|
109 |
+
config: main
|
110 |
+
split: test
|
111 |
+
args:
|
112 |
+
num_few_shot: 5
|
113 |
+
metrics:
|
114 |
+
- type: acc
|
115 |
+
value: 10.69
|
116 |
+
name: accuracy
|
117 |
+
source:
|
118 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Gemmalpaca-2B
|
119 |
+
name: Open LLM Leaderboard
|
120 |
+
---
|
121 |
+
|
122 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
123 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
124 |
+
</div>
|
125 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
126 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
127 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
128 |
+
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>
|
129 |
+
</p>
|
130 |
+
</div>
|
131 |
+
</div>
|
132 |
+
|
133 |
+
## mlabonne/Gemmalpaca-2B - GGUF
|
134 |
+
|
135 |
+
This repo contains GGUF format model files for [mlabonne/Gemmalpaca-2B](https://huggingface.co/mlabonne/Gemmalpaca-2B).
|
136 |
+
|
137 |
+
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).
|
138 |
+
|
139 |
+
<div style="text-align: left; margin: 20px 0;">
|
140 |
+
<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;">
|
141 |
+
Run them on the TensorBlock client using your local machine ↗
|
142 |
+
</a>
|
143 |
+
</div>
|
144 |
+
|
145 |
+
## Prompt template
|
146 |
+
|
147 |
+
```
|
148 |
+
|
149 |
+
```
|
150 |
+
|
151 |
+
## Model file specification
|
152 |
+
|
153 |
+
| Filename | Quant type | File Size | Description |
|
154 |
+
| -------- | ---------- | --------- | ----------- |
|
155 |
+
| [Gemmalpaca-2B-Q2_K.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q2_K.gguf) | Q2_K | 1.158 GB | smallest, significant quality loss - not recommended for most purposes |
|
156 |
+
| [Gemmalpaca-2B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q3_K_S.gguf) | Q3_K_S | 1.288 GB | very small, high quality loss |
|
157 |
+
| [Gemmalpaca-2B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q3_K_M.gguf) | Q3_K_M | 1.384 GB | very small, high quality loss |
|
158 |
+
| [Gemmalpaca-2B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q3_K_L.gguf) | Q3_K_L | 1.466 GB | small, substantial quality loss |
|
159 |
+
| [Gemmalpaca-2B-Q4_0.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q4_0.gguf) | Q4_0 | 1.551 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
160 |
+
| [Gemmalpaca-2B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q4_K_S.gguf) | Q4_K_S | 1.560 GB | small, greater quality loss |
|
161 |
+
| [Gemmalpaca-2B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q4_K_M.gguf) | Q4_K_M | 1.630 GB | medium, balanced quality - recommended |
|
162 |
+
| [Gemmalpaca-2B-Q5_0.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q5_0.gguf) | Q5_0 | 1.799 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
163 |
+
| [Gemmalpaca-2B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q5_K_S.gguf) | Q5_K_S | 1.799 GB | large, low quality loss - recommended |
|
164 |
+
| [Gemmalpaca-2B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q5_K_M.gguf) | Q5_K_M | 1.840 GB | large, very low quality loss - recommended |
|
165 |
+
| [Gemmalpaca-2B-Q6_K.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q6_K.gguf) | Q6_K | 2.062 GB | very large, extremely low quality loss |
|
166 |
+
| [Gemmalpaca-2B-Q8_0.gguf](https://huggingface.co/tensorblock/Gemmalpaca-2B-GGUF/blob/main/Gemmalpaca-2B-Q8_0.gguf) | Q8_0 | 2.669 GB | very large, extremely low quality loss - not recommended |
|
167 |
+
|
168 |
+
|
169 |
+
## Downloading instruction
|
170 |
+
|
171 |
+
### Command line
|
172 |
+
|
173 |
+
Firstly, install Huggingface Client
|
174 |
+
|
175 |
+
```shell
|
176 |
+
pip install -U "huggingface_hub[cli]"
|
177 |
+
```
|
178 |
+
|
179 |
+
Then, downoad the individual model file the a local directory
|
180 |
+
|
181 |
+
```shell
|
182 |
+
huggingface-cli download tensorblock/Gemmalpaca-2B-GGUF --include "Gemmalpaca-2B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
183 |
+
```
|
184 |
+
|
185 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
186 |
+
|
187 |
+
```shell
|
188 |
+
huggingface-cli download tensorblock/Gemmalpaca-2B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
189 |
+
```
|