Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +195 -0
- math_gpt2_sft-Q2_K.gguf +3 -0
- math_gpt2_sft-Q3_K_L.gguf +3 -0
- math_gpt2_sft-Q3_K_M.gguf +3 -0
- math_gpt2_sft-Q3_K_S.gguf +3 -0
- math_gpt2_sft-Q4_0.gguf +3 -0
- math_gpt2_sft-Q4_K_M.gguf +3 -0
- math_gpt2_sft-Q4_K_S.gguf +3 -0
- math_gpt2_sft-Q5_0.gguf +3 -0
- math_gpt2_sft-Q5_K_M.gguf +3 -0
- math_gpt2_sft-Q5_K_S.gguf +3 -0
- math_gpt2_sft-Q6_K.gguf +3 -0
- math_gpt2_sft-Q8_0.gguf +3 -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 |
+
math_gpt2_sft-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
math_gpt2_sft-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
math_gpt2_sft-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
math_gpt2_sft-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
math_gpt2_sft-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
math_gpt2_sft-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
math_gpt2_sft-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
math_gpt2_sft-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
math_gpt2_sft-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
math_gpt2_sft-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
math_gpt2_sft-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
math_gpt2_sft-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- maths
|
7 |
+
- gpt2
|
8 |
+
- mathgpt2
|
9 |
+
- trl
|
10 |
+
- sft
|
11 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
datasets:
|
14 |
+
- meta-math/MetaMathQA
|
15 |
+
- ArtifactAI/arxiv-math-instruct-50k
|
16 |
+
pipeline_tag: text-generation
|
17 |
+
widget:
|
18 |
+
- text: Which motion is formed by an incident particle?
|
19 |
+
example_title: Example 1
|
20 |
+
- text: What type of diffusional modeling is used for diffusion?
|
21 |
+
example_title: Example 2
|
22 |
+
base_model: Sharathhebbar24/math_gpt2_sft
|
23 |
+
model-index:
|
24 |
+
- name: math_gpt2_sft
|
25 |
+
results:
|
26 |
+
- task:
|
27 |
+
type: text-generation
|
28 |
+
name: Text Generation
|
29 |
+
dataset:
|
30 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
31 |
+
type: ai2_arc
|
32 |
+
config: ARC-Challenge
|
33 |
+
split: test
|
34 |
+
args:
|
35 |
+
num_few_shot: 25
|
36 |
+
metrics:
|
37 |
+
- type: acc_norm
|
38 |
+
value: 22.87
|
39 |
+
name: normalized accuracy
|
40 |
+
source:
|
41 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/math_gpt2_sft
|
42 |
+
name: Open LLM Leaderboard
|
43 |
+
- task:
|
44 |
+
type: text-generation
|
45 |
+
name: Text Generation
|
46 |
+
dataset:
|
47 |
+
name: HellaSwag (10-Shot)
|
48 |
+
type: hellaswag
|
49 |
+
split: validation
|
50 |
+
args:
|
51 |
+
num_few_shot: 10
|
52 |
+
metrics:
|
53 |
+
- type: acc_norm
|
54 |
+
value: 30.41
|
55 |
+
name: normalized accuracy
|
56 |
+
source:
|
57 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/math_gpt2_sft
|
58 |
+
name: Open LLM Leaderboard
|
59 |
+
- task:
|
60 |
+
type: text-generation
|
61 |
+
name: Text Generation
|
62 |
+
dataset:
|
63 |
+
name: MMLU (5-Shot)
|
64 |
+
type: cais/mmlu
|
65 |
+
config: all
|
66 |
+
split: test
|
67 |
+
args:
|
68 |
+
num_few_shot: 5
|
69 |
+
metrics:
|
70 |
+
- type: acc
|
71 |
+
value: 25.06
|
72 |
+
name: accuracy
|
73 |
+
source:
|
74 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/math_gpt2_sft
|
75 |
+
name: Open LLM Leaderboard
|
76 |
+
- task:
|
77 |
+
type: text-generation
|
78 |
+
name: Text Generation
|
79 |
+
dataset:
|
80 |
+
name: TruthfulQA (0-shot)
|
81 |
+
type: truthful_qa
|
82 |
+
config: multiple_choice
|
83 |
+
split: validation
|
84 |
+
args:
|
85 |
+
num_few_shot: 0
|
86 |
+
metrics:
|
87 |
+
- type: mc2
|
88 |
+
value: 37.62
|
89 |
+
source:
|
90 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/math_gpt2_sft
|
91 |
+
name: Open LLM Leaderboard
|
92 |
+
- task:
|
93 |
+
type: text-generation
|
94 |
+
name: Text Generation
|
95 |
+
dataset:
|
96 |
+
name: Winogrande (5-shot)
|
97 |
+
type: winogrande
|
98 |
+
config: winogrande_xl
|
99 |
+
split: validation
|
100 |
+
args:
|
101 |
+
num_few_shot: 5
|
102 |
+
metrics:
|
103 |
+
- type: acc
|
104 |
+
value: 51.54
|
105 |
+
name: accuracy
|
106 |
+
source:
|
107 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/math_gpt2_sft
|
108 |
+
name: Open LLM Leaderboard
|
109 |
+
- task:
|
110 |
+
type: text-generation
|
111 |
+
name: Text Generation
|
112 |
+
dataset:
|
113 |
+
name: GSM8k (5-shot)
|
114 |
+
type: gsm8k
|
115 |
+
config: main
|
116 |
+
split: test
|
117 |
+
args:
|
118 |
+
num_few_shot: 5
|
119 |
+
metrics:
|
120 |
+
- type: acc
|
121 |
+
value: 0.68
|
122 |
+
name: accuracy
|
123 |
+
source:
|
124 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Sharathhebbar24/math_gpt2_sft
|
125 |
+
name: Open LLM Leaderboard
|
126 |
+
---
|
127 |
+
|
128 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
129 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
130 |
+
</div>
|
131 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
132 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
133 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
134 |
+
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>
|
135 |
+
</p>
|
136 |
+
</div>
|
137 |
+
</div>
|
138 |
+
|
139 |
+
## Sharathhebbar24/math_gpt2_sft - GGUF
|
140 |
+
|
141 |
+
This repo contains GGUF format model files for [Sharathhebbar24/math_gpt2_sft](https://huggingface.co/Sharathhebbar24/math_gpt2_sft).
|
142 |
+
|
143 |
+
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).
|
144 |
+
|
145 |
+
<div style="text-align: left; margin: 20px 0;">
|
146 |
+
<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;">
|
147 |
+
Run them on the TensorBlock client using your local machine ↗
|
148 |
+
</a>
|
149 |
+
</div>
|
150 |
+
|
151 |
+
## Prompt template
|
152 |
+
|
153 |
+
```
|
154 |
+
|
155 |
+
```
|
156 |
+
|
157 |
+
## Model file specification
|
158 |
+
|
159 |
+
| Filename | Quant type | File Size | Description |
|
160 |
+
| -------- | ---------- | --------- | ----------- |
|
161 |
+
| [math_gpt2_sft-Q2_K.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q2_K.gguf) | Q2_K | 0.081 GB | smallest, significant quality loss - not recommended for most purposes |
|
162 |
+
| [math_gpt2_sft-Q3_K_S.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q3_K_S.gguf) | Q3_K_S | 0.090 GB | very small, high quality loss |
|
163 |
+
| [math_gpt2_sft-Q3_K_M.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q3_K_M.gguf) | Q3_K_M | 0.098 GB | very small, high quality loss |
|
164 |
+
| [math_gpt2_sft-Q3_K_L.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q3_K_L.gguf) | Q3_K_L | 0.102 GB | small, substantial quality loss |
|
165 |
+
| [math_gpt2_sft-Q4_0.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q4_0.gguf) | Q4_0 | 0.107 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
166 |
+
| [math_gpt2_sft-Q4_K_S.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q4_K_S.gguf) | Q4_K_S | 0.107 GB | small, greater quality loss |
|
167 |
+
| [math_gpt2_sft-Q4_K_M.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q4_K_M.gguf) | Q4_K_M | 0.113 GB | medium, balanced quality - recommended |
|
168 |
+
| [math_gpt2_sft-Q5_0.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q5_0.gguf) | Q5_0 | 0.122 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
169 |
+
| [math_gpt2_sft-Q5_K_S.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q5_K_S.gguf) | Q5_K_S | 0.122 GB | large, low quality loss - recommended |
|
170 |
+
| [math_gpt2_sft-Q5_K_M.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q5_K_M.gguf) | Q5_K_M | 0.127 GB | large, very low quality loss - recommended |
|
171 |
+
| [math_gpt2_sft-Q6_K.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q6_K.gguf) | Q6_K | 0.138 GB | very large, extremely low quality loss |
|
172 |
+
| [math_gpt2_sft-Q8_0.gguf](https://huggingface.co/tensorblock/math_gpt2_sft-GGUF/blob/main/math_gpt2_sft-Q8_0.gguf) | Q8_0 | 0.178 GB | very large, extremely low quality loss - not recommended |
|
173 |
+
|
174 |
+
|
175 |
+
## Downloading instruction
|
176 |
+
|
177 |
+
### Command line
|
178 |
+
|
179 |
+
Firstly, install Huggingface Client
|
180 |
+
|
181 |
+
```shell
|
182 |
+
pip install -U "huggingface_hub[cli]"
|
183 |
+
```
|
184 |
+
|
185 |
+
Then, downoad the individual model file the a local directory
|
186 |
+
|
187 |
+
```shell
|
188 |
+
huggingface-cli download tensorblock/math_gpt2_sft-GGUF --include "math_gpt2_sft-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
189 |
+
```
|
190 |
+
|
191 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
192 |
+
|
193 |
+
```shell
|
194 |
+
huggingface-cli download tensorblock/math_gpt2_sft-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
195 |
+
```
|
math_gpt2_sft-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b53ec80cf8fab3ebc9888592bd8636063b0d6559e272e513b7a3c02fe89880e8
|
3 |
+
size 81197216
|
math_gpt2_sft-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4679b8c5859fa15488c99c53c932275dc10b7b3e2acfce2890b34bd90b8e4106
|
3 |
+
size 102093152
|
math_gpt2_sft-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9a839b341a0ce671d3b79692188eea701c3b7b0b24030a173e2f23a29aef3fe
|
3 |
+
size 97669472
|
math_gpt2_sft-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86fc80388e5285daded73490900999b8dd3b4c2c070c12c7e138232a922c5777
|
3 |
+
size 90149216
|
math_gpt2_sft-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6be51550a0fd4ff0bdb1c375f4276bdc69ab74b9a43d81af975e7febd34787c2
|
3 |
+
size 106555808
|
math_gpt2_sft-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19afed4b6365ea9cfa1de2c9362049c8cf3238b9d0216999b0f876f1d91a5f66
|
3 |
+
size 112859552
|
math_gpt2_sft-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea4a15297b6e5c6e507cd283c1a469f5461e5e2a6320195290a3e1767e13c9f7
|
3 |
+
size 106850720
|
math_gpt2_sft-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdcdcaddb637d2c4e2f397ff3db969cdba17f27b1ac2a9754dcabb230fb729db
|
3 |
+
size 121997312
|
math_gpt2_sft-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff67b555f644dfbd7c3bcdd0e30c6ed065ed2946b9d11759e491990964211cb1
|
3 |
+
size 126697472
|
math_gpt2_sft-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c1e32325c6213f30ff4af68fd68c2e5148f4db81cfbb590d34e479eb21e5bf
|
3 |
+
size 121997312
|
math_gpt2_sft-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f63dff88bd65cd8f86f080cbaa289ce7432c53a84546821dd166ad65199cdb6f
|
3 |
+
size 138403904
|
math_gpt2_sft-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4474aaacb9ae5f6e67284460313b9fdd4c3ce21ed761712a7fc6b5c9783018a8
|
3 |
+
size 177669632
|