Upload folder using huggingface_hub
Browse files- .gitattributes +14 -0
- README.md +124 -0
- wizardmath-7b-v1.1.Q2_K.gguf +3 -0
- wizardmath-7b-v1.1.Q3_K_L.gguf +3 -0
- wizardmath-7b-v1.1.Q3_K_M.gguf +3 -0
- wizardmath-7b-v1.1.Q3_K_S.gguf +3 -0
- wizardmath-7b-v1.1.Q4_0.gguf +3 -0
- wizardmath-7b-v1.1.Q4_1.gguf +3 -0
- wizardmath-7b-v1.1.Q4_K_M.gguf +3 -0
- wizardmath-7b-v1.1.Q4_K_S.gguf +3 -0
- wizardmath-7b-v1.1.Q5_0.gguf +3 -0
- wizardmath-7b-v1.1.Q5_1.gguf +3 -0
- wizardmath-7b-v1.1.Q5_K_M.gguf +3 -0
- wizardmath-7b-v1.1.Q5_K_S.gguf +3 -0
- wizardmath-7b-v1.1.Q6_K.gguf +3 -0
- wizardmath-7b-v1.1.Q8_0.gguf +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,17 @@ 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 |
+
wizardmath-7b-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
wizardmath-7b-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
wizardmath-7b-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
wizardmath-7b-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
wizardmath-7b-v1.1.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
wizardmath-7b-v1.1.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
wizardmath-7b-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
wizardmath-7b-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
wizardmath-7b-v1.1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
wizardmath-7b-v1.1.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
wizardmath-7b-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
wizardmath-7b-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
wizardmath-7b-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
49 |
+
wizardmath-7b-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: "WizardMath-7B-V1.1 Quantized in GGUF"
|
3 |
+
tags:
|
4 |
+
- GGUF
|
5 |
+
language: en
|
6 |
+
---
|
7 |
+
![Image description](https://i.postimg.cc/MGwhtFfF/tsune-fixed.png)
|
8 |
+
|
9 |
+
# Tsunemoto GGUF's of WizardMath-7B-V1.1
|
10 |
+
|
11 |
+
This is a GGUF quantization of WizardMath-7B-V1.1.
|
12 |
+
|
13 |
+
## Original Repo Link:
|
14 |
+
[Original Repository](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
|
15 |
+
|
16 |
+
## Original Model Card:
|
17 |
+
---
|
18 |
+
|
19 |
+
|
20 |
+
## WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct (RLEIF)
|
21 |
+
|
22 |
+
<p style="font-size:28px;" align="center">
|
23 |
+
🏠 <a href="https://wizardlm.github.io/" target="_blank">Home Page</a> </p>
|
24 |
+
<p align="center">
|
25 |
+
<p align="center">
|
26 |
+
🤗 <a href="https://huggingface.co/WizardLM" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/nlpxucan/WizardLM" target="_blank">Github Repo</a> • 🐦 <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> </p>
|
27 |
+
<p align="center">
|
28 |
+
📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> • 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> • 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>
|
29 |
+
</p>
|
30 |
+
<p align="center">
|
31 |
+
👋 Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>
|
32 |
+
</p>
|
33 |
+
|
34 |
+
## News
|
35 |
+
|
36 |
+
[12/19/2023] 🔥 We released **WizardMath-7B-V1.1** trained from Mistral-7B, the **SOTA 7B math LLM**, achieves **83.2 pass@1** on GSM8k, and **33.0 pass@1** on MATH.
|
37 |
+
|
38 |
+
[12/19/2023] 🔥 **WizardMath-7B-V1.1** outperforms **ChatGPT 3.5**, **Gemini Pro**, **Mixtral MOE**, and **Claude Instant** on GSM8K pass@1.
|
39 |
+
|
40 |
+
[12/19/2023] 🔥 **WizardMath-7B-V1.1** is comparable with **ChatGPT 3.5**, **Gemini Pro**, and surpasses **Mixtral MOE** on MATH pass@1.
|
41 |
+
|
42 |
+
| Model | Checkpoint | Paper | GSM8k | MATH |
|
43 |
+
| ----- |------| ---- |------|-------|
|
44 |
+
| **WizardMath-7B-V1.1** | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **83.2** | **33.0** |
|
45 |
+
| WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |
|
46 |
+
| WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |
|
47 |
+
| WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** |
|
48 |
+
|
49 |
+
|
50 |
+
## [12/19/2023] Comparing WizardMath-7B-V1.1 with other open source 7B size math LLMs.
|
51 |
+
|
52 |
+
| Model | GSM8k Pass@1 | MATH Pass@1 |
|
53 |
+
| ----- |------| ---- |
|
54 |
+
| MPT-7B | 6.8 | 3.0 |
|
55 |
+
|Llama 1-7B | 11.0 | 2.9 |
|
56 |
+
|Llama 2-7B|12.3 |2.8 |
|
57 |
+
|Yi-6b| 32.6 |5.8 |
|
58 |
+
|Mistral-7B|37.8 |9.1 |
|
59 |
+
|Qwen-7b|47.8 |9.3 |
|
60 |
+
| RFT-7B | 50.3 | -- |
|
61 |
+
| MAmmoTH-7B (COT) | 50.5 | 10.4 |
|
62 |
+
| WizardMath-7B-V1.0 | 54.9 | 10.7 |
|
63 |
+
|Abel-7B-001 |59.7 |13 |
|
64 |
+
| MetaMath-7B | 66.5 | 19.8 |
|
65 |
+
| Arithmo-Mistral-7B | 74.7 | 25.3 |
|
66 |
+
|MetaMath-Mistral-7B|77.7 |28.2 |
|
67 |
+
|Abel-7B-002 | 80.4 | 29.5 |
|
68 |
+
| **WizardMath-7B-V1.1** | **83.2** | **33.0** |
|
69 |
+
|
70 |
+
|
71 |
+
## [12/19/2023] Comparing WizardMath-7B-V1.1 with large open source (30B~70B) LLMs.
|
72 |
+
|
73 |
+
| Model | GSM8k Pass@1 | MATH Pass@1 |
|
74 |
+
| ----- |------| ---- |
|
75 |
+
| Llemma-34B | 51.5 | 25.0 |
|
76 |
+
| Minerva-62B | 52.4 | 27.6 |
|
77 |
+
| Llama 2-70B | 56.8 | 13.5 |
|
78 |
+
| DeepSeek 67B | 63.4 | -- |
|
79 |
+
| Gork 33B | 62.9 | 23.9 |
|
80 |
+
| MAmmoTH-70B | 72.4 | 21.1 |
|
81 |
+
| Yi-34B | 67.9 | 15.9 |
|
82 |
+
| Mixtral 8x7B | 74.4 | 28.4 |
|
83 |
+
| MetaMath-70B | 82.3 | 26.6 |
|
84 |
+
| **WizardMath-7B-V1.1** | **83.2** | **33.0** |
|
85 |
+
|
86 |
+
|
87 |
+
🔥
|
88 |
+
❗<b>Note for model system prompts usage:</b>
|
89 |
+
|
90 |
+
Please use **the same systems prompts strictly** with us, and we do not guarantee the accuracy of the **quantified versions**.
|
91 |
+
|
92 |
+
**Default version:**
|
93 |
+
|
94 |
+
```
|
95 |
+
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
|
96 |
+
```
|
97 |
+
|
98 |
+
|
99 |
+
**CoT Version:** (❗For the **simple** math questions, we do NOT recommend to use the CoT prompt.)
|
100 |
+
|
101 |
+
|
102 |
+
```
|
103 |
+
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: Let's think step by step."
|
104 |
+
```
|
105 |
+
|
106 |
+
## Inference WizardMath Demo Script
|
107 |
+
|
108 |
+
We provide the WizardMath inference demo code [here](https://github.com/nlpxucan/WizardLM/tree/main/demo).
|
109 |
+
|
110 |
+
|
111 |
+
|
112 |
+
|
113 |
+
## Citation
|
114 |
+
|
115 |
+
Please cite the repo if you use the data, method or code in this repo.
|
116 |
+
|
117 |
+
```
|
118 |
+
@article{luo2023wizardmath,
|
119 |
+
title={WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct},
|
120 |
+
author={Luo, Haipeng and Sun, Qingfeng and Xu, Can and Zhao, Pu and Lou, Jianguang and Tao, Chongyang and Geng, Xiubo and Lin, Qingwei and Chen, Shifeng and Zhang, Dongmei},
|
121 |
+
journal={arXiv preprint arXiv:2308.09583},
|
122 |
+
year={2023}
|
123 |
+
}
|
124 |
+
```
|
wizardmath-7b-v1.1.Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:042145ebc57c3438e36bbeafcfb2e553fb92bda9b768cb4f44ab1ef272500550
|
3 |
+
size 3084034080
|
wizardmath-7b-v1.1.Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d6f2bb4106d36eaccd00021992257d5334e9780b3901406211c2d2ea16e1f9a
|
3 |
+
size 3822960672
|
wizardmath-7b-v1.1.Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff859ecdda4971600012c78ca92b3c6619f9987363157778f64a49e7becf0908
|
3 |
+
size 3519922208
|
wizardmath-7b-v1.1.Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc1b7aa2c1b87d2834da4ed3b6ac68dae3ba33feec1ac81729393455077a10be
|
3 |
+
size 3165503520
|
wizardmath-7b-v1.1.Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e55396f1a7d4a786e78ae882198c597182a2637ffd9a4e9e40398c15633531b6
|
3 |
+
size 4109852704
|
wizardmath-7b-v1.1.Q4_1.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b39a8e411c65b257ba1e8468822177a60ca649ede85001b86ef6b85bae27d7e
|
3 |
+
size 4554252320
|
wizardmath-7b-v1.1.Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:575023ff641df2514caf9711fea7e10862055b702e2d79e87a45abb4c08ce585
|
3 |
+
size 4369375264
|
wizardmath-7b-v1.1.Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46f2047205cbdb5f37c651fd38751f3580d38ba7ceffa96ae0436cf46dfe7c14
|
3 |
+
size 4141309984
|
wizardmath-7b-v1.1.Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73723d2ee88095846f4d78649018136862a349ab7acb9888e3f4c51ad0709a43
|
3 |
+
size 4998651936
|
wizardmath-7b-v1.1.Q5_1.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abb226b7a71373f0499b984f3280771deee224cc92b04eebc5ab6d8642ca0611
|
3 |
+
size 5443051552
|
wizardmath-7b-v1.1.Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95ee56846ce64966d32c83a621cd67641e9ee5c86b7e58ac7888a8fe2a2d9e54
|
3 |
+
size 5132345376
|
wizardmath-7b-v1.1.Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2af9d51bc499ad15c3db1887e78ef66c66bb7df7a92be3e10cb0e090fa3437e
|
3 |
+
size 4998651936
|
wizardmath-7b-v1.1.Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c63940650dc688703b464b9b3fe52cee1adca4e191a69ac1a20ac5a785116f0
|
3 |
+
size 5943001120
|
wizardmath-7b-v1.1.Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c2620d3c7b1cfdfd206b15eb46ada42a7cee6088ad9884fd9d9c0b3b5a061f
|
3 |
+
size 7696793632
|