Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +110 -0
- gpt2-xl-conversational-Q2_K.gguf +3 -0
- gpt2-xl-conversational-Q3_K_L.gguf +3 -0
- gpt2-xl-conversational-Q3_K_M.gguf +3 -0
- gpt2-xl-conversational-Q3_K_S.gguf +3 -0
- gpt2-xl-conversational-Q4_0.gguf +3 -0
- gpt2-xl-conversational-Q4_K_M.gguf +3 -0
- gpt2-xl-conversational-Q4_K_S.gguf +3 -0
- gpt2-xl-conversational-Q5_0.gguf +3 -0
- gpt2-xl-conversational-Q5_K_M.gguf +3 -0
- gpt2-xl-conversational-Q5_K_S.gguf +3 -0
- gpt2-xl-conversational-Q6_K.gguf +3 -0
- gpt2-xl-conversational-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 |
+
gpt2-xl-conversational-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
gpt2-xl-conversational-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
gpt2-xl-conversational-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
gpt2-xl-conversational-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
gpt2-xl-conversational-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
gpt2-xl-conversational-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
gpt2-xl-conversational-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
gpt2-xl-conversational-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
gpt2-xl-conversational-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
gpt2-xl-conversational-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
gpt2-xl-conversational-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
gpt2-xl-conversational-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
datasets:
|
4 |
+
- Locutusque/InstructMix
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
metrics:
|
8 |
+
- bleu
|
9 |
+
- perplexity
|
10 |
+
- loss
|
11 |
+
- accuracy
|
12 |
+
pipeline_tag: text-generation
|
13 |
+
widget:
|
14 |
+
- text: '<|USER|> Design a Neo4j database and Cypher function snippet to Display Extreme
|
15 |
+
Dental hygiene: Using Mouthwash for Analysis for Beginners. Implement if/else
|
16 |
+
or switch/case statements to handle different conditions related to the Consent.
|
17 |
+
Provide detailed comments explaining your control flow and the reasoning behind
|
18 |
+
each decision. <|ASSISTANT|> '
|
19 |
+
- text: '<|USER|> Write me a story about a magical place. <|ASSISTANT|> '
|
20 |
+
- text: '<|USER|> Write me an essay about the life of George Washington <|ASSISTANT|> '
|
21 |
+
- text: '<|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|> '
|
22 |
+
- text: '<|USER|> Craft me a list of some nice places to visit around the world. <|ASSISTANT|> '
|
23 |
+
- text: '<|USER|> How to manage a lazy employee: Address the employee verbally. Don''t
|
24 |
+
allow an employee''s laziness or lack of enthusiasm to become a recurring issue.
|
25 |
+
Tell the employee you''re hoping to speak with them about workplace expectations
|
26 |
+
and performance, and schedule a time to sit down together. Question: To manage
|
27 |
+
a lazy employee, it is suggested to talk to the employee. True, False, or Neither?
|
28 |
+
<|ASSISTANT|> '
|
29 |
+
inference:
|
30 |
+
parameters:
|
31 |
+
temperature: 0.8
|
32 |
+
do_sample: true
|
33 |
+
top_p: 0.14
|
34 |
+
top_k: 41
|
35 |
+
max_new_tokens: 250
|
36 |
+
repetition_penalty: 1.176
|
37 |
+
base_model: Locutusque/gpt2-xl-conversational
|
38 |
+
tags:
|
39 |
+
- TensorBlock
|
40 |
+
- GGUF
|
41 |
+
---
|
42 |
+
|
43 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
44 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
45 |
+
</div>
|
46 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
47 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
48 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
49 |
+
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>
|
50 |
+
</p>
|
51 |
+
</div>
|
52 |
+
</div>
|
53 |
+
|
54 |
+
## Locutusque/gpt2-xl-conversational - GGUF
|
55 |
+
|
56 |
+
This repo contains GGUF format model files for [Locutusque/gpt2-xl-conversational](https://huggingface.co/Locutusque/gpt2-xl-conversational).
|
57 |
+
|
58 |
+
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).
|
59 |
+
|
60 |
+
<div style="text-align: left; margin: 20px 0;">
|
61 |
+
<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;">
|
62 |
+
Run them on the TensorBlock client using your local machine ↗
|
63 |
+
</a>
|
64 |
+
</div>
|
65 |
+
|
66 |
+
## Prompt template
|
67 |
+
|
68 |
+
```
|
69 |
+
|
70 |
+
```
|
71 |
+
|
72 |
+
## Model file specification
|
73 |
+
|
74 |
+
| Filename | Quant type | File Size | Description |
|
75 |
+
| -------- | ---------- | --------- | ----------- |
|
76 |
+
| [gpt2-xl-conversational-Q2_K.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q2_K.gguf) | Q2_K | 0.845 GB | smallest, significant quality loss - not recommended for most purposes |
|
77 |
+
| [gpt2-xl-conversational-Q3_K_S.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q3_K_S.gguf) | Q3_K_S | 0.845 GB | very small, high quality loss |
|
78 |
+
| [gpt2-xl-conversational-Q3_K_M.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q3_K_M.gguf) | Q3_K_M | 0.966 GB | very small, high quality loss |
|
79 |
+
| [gpt2-xl-conversational-Q3_K_L.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q3_K_L.gguf) | Q3_K_L | 1.027 GB | small, substantial quality loss |
|
80 |
+
| [gpt2-xl-conversational-Q4_0.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q4_0.gguf) | Q4_0 | 0.906 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
81 |
+
| [gpt2-xl-conversational-Q4_K_S.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q4_K_S.gguf) | Q4_K_S | 1.037 GB | small, greater quality loss |
|
82 |
+
| [gpt2-xl-conversational-Q4_K_M.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q4_K_M.gguf) | Q4_K_M | 1.110 GB | medium, balanced quality - recommended |
|
83 |
+
| [gpt2-xl-conversational-Q5_0.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q5_0.gguf) | Q5_0 | 1.087 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
84 |
+
| [gpt2-xl-conversational-Q5_K_S.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q5_K_S.gguf) | Q5_K_S | 1.149 GB | large, low quality loss - recommended |
|
85 |
+
| [gpt2-xl-conversational-Q5_K_M.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q5_K_M.gguf) | Q5_K_M | 1.286 GB | large, very low quality loss - recommended |
|
86 |
+
| [gpt2-xl-conversational-Q6_K.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q6_K.gguf) | Q6_K | 1.519 GB | very large, extremely low quality loss |
|
87 |
+
| [gpt2-xl-conversational-Q8_0.gguf](https://huggingface.co/tensorblock/gpt2-xl-conversational-GGUF/blob/main/gpt2-xl-conversational-Q8_0.gguf) | Q8_0 | 1.630 GB | very large, extremely low quality loss - not recommended |
|
88 |
+
|
89 |
+
|
90 |
+
## Downloading instruction
|
91 |
+
|
92 |
+
### Command line
|
93 |
+
|
94 |
+
Firstly, install Huggingface Client
|
95 |
+
|
96 |
+
```shell
|
97 |
+
pip install -U "huggingface_hub[cli]"
|
98 |
+
```
|
99 |
+
|
100 |
+
Then, downoad the individual model file the a local directory
|
101 |
+
|
102 |
+
```shell
|
103 |
+
huggingface-cli download tensorblock/gpt2-xl-conversational-GGUF --include "gpt2-xl-conversational-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
104 |
+
```
|
105 |
+
|
106 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
107 |
+
|
108 |
+
```shell
|
109 |
+
huggingface-cli download tensorblock/gpt2-xl-conversational-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
110 |
+
```
|
gpt2-xl-conversational-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:174fbb3deb18a02db020819fec6461a94f478f379862824de91a32cee30bb5f9
|
3 |
+
size 907195808
|
gpt2-xl-conversational-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3273777ec3dd96592d3a6a7e1c491982653a4cd38b74e355c93dd722371879c7
|
3 |
+
size 1103035808
|
gpt2-xl-conversational-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:447bf4a8d066613fa5f7be4e6542e53aa009b1fbb9ff402587350f880053e125
|
3 |
+
size 1037755808
|
gpt2-xl-conversational-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07055b10340aa4a0edc607cfffad6a4bffb92a077914d634ac7a477b06357a7f
|
3 |
+
size 907195808
|
gpt2-xl-conversational-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:100e2cad0585baa7abc7ded8563dc4522a2277dc0e689611777f8a966ef4e7b5
|
3 |
+
size 972475808
|
gpt2-xl-conversational-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b571c550e4d72ae32fde1dbd5562bfa9931d31cf6e95b19ce13c01dd27143d4
|
3 |
+
size 1191807808
|
gpt2-xl-conversational-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d625bf25831e05a792e62b73321b26497faf736f0edda11a841f9ff4a5615351
|
3 |
+
size 1113087808
|
gpt2-xl-conversational-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f138f281c989397f4aadea7cadfc614187de8b910bd651865394856e7045044c
|
3 |
+
size 1166847808
|
gpt2-xl-conversational-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a399221c38a69992a96710cb52c5382eaf3829b87a6837a2bbfb9dccec7307be
|
3 |
+
size 1381153792
|
gpt2-xl-conversational-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4ca18cce1835020c0961ed619b4b00fe5b641f4b2d3d232dca67b91fc726e91
|
3 |
+
size 1233313792
|
gpt2-xl-conversational-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00f06d4820b422a81a68698eece73c08fe7f3dcc495c1835c5fc9db4181d0339
|
3 |
+
size 1630923808
|
gpt2-xl-conversational-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ed4f62478c1d52d6b55f956d14c02fd292c91b514ded68f4b8fbc4fa7337bb7
|
3 |
+
size 1749963808
|