Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +101 -0
- speechless-coding-7b-16k-tora-Q2_K.gguf +3 -0
- speechless-coding-7b-16k-tora-Q3_K_L.gguf +3 -0
- speechless-coding-7b-16k-tora-Q3_K_M.gguf +3 -0
- speechless-coding-7b-16k-tora-Q3_K_S.gguf +3 -0
- speechless-coding-7b-16k-tora-Q4_0.gguf +3 -0
- speechless-coding-7b-16k-tora-Q4_K_M.gguf +3 -0
- speechless-coding-7b-16k-tora-Q4_K_S.gguf +3 -0
- speechless-coding-7b-16k-tora-Q5_0.gguf +3 -0
- speechless-coding-7b-16k-tora-Q5_K_M.gguf +3 -0
- speechless-coding-7b-16k-tora-Q5_K_S.gguf +3 -0
- speechless-coding-7b-16k-tora-Q6_K.gguf +3 -0
- speechless-coding-7b-16k-tora-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 |
+
speechless-coding-7b-16k-tora-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
speechless-coding-7b-16k-tora-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
speechless-coding-7b-16k-tora-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
speechless-coding-7b-16k-tora-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
speechless-coding-7b-16k-tora-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
speechless-coding-7b-16k-tora-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
speechless-coding-7b-16k-tora-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
speechless-coding-7b-16k-tora-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
speechless-coding-7b-16k-tora-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
speechless-coding-7b-16k-tora-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
speechless-coding-7b-16k-tora-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
speechless-coding-7b-16k-tora-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
library_name: transformers
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
datasets:
|
7 |
+
- jondurbin/airoboros-2.2
|
8 |
+
- Open-Orca/OpenOrca
|
9 |
+
- garage-bAInd/Open-Platypus
|
10 |
+
- WizardLM/WizardLM_evol_instruct_V2_196k
|
11 |
+
- TokenBender/python_eval_instruct_51k
|
12 |
+
tags:
|
13 |
+
- llama-2
|
14 |
+
- code
|
15 |
+
- TensorBlock
|
16 |
+
- GGUF
|
17 |
+
license: llama2
|
18 |
+
base_model: uukuguy/speechless-coding-7b-16k-tora
|
19 |
+
model-index:
|
20 |
+
- name: SpeechlessCoder
|
21 |
+
results:
|
22 |
+
- task:
|
23 |
+
type: text-generation
|
24 |
+
dataset:
|
25 |
+
name: HumanEval
|
26 |
+
type: openai_humaneval
|
27 |
+
metrics:
|
28 |
+
- type: pass@1
|
29 |
+
value: 52.439
|
30 |
+
name: pass@1
|
31 |
+
verified: false
|
32 |
+
---
|
33 |
+
|
34 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
35 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
36 |
+
</div>
|
37 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
38 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
39 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
40 |
+
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>
|
41 |
+
</p>
|
42 |
+
</div>
|
43 |
+
</div>
|
44 |
+
|
45 |
+
## uukuguy/speechless-coding-7b-16k-tora - GGUF
|
46 |
+
|
47 |
+
This repo contains GGUF format model files for [uukuguy/speechless-coding-7b-16k-tora](https://huggingface.co/uukuguy/speechless-coding-7b-16k-tora).
|
48 |
+
|
49 |
+
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).
|
50 |
+
|
51 |
+
<div style="text-align: left; margin: 20px 0;">
|
52 |
+
<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;">
|
53 |
+
Run them on the TensorBlock client using your local machine ↗
|
54 |
+
</a>
|
55 |
+
</div>
|
56 |
+
|
57 |
+
## Prompt template
|
58 |
+
|
59 |
+
```
|
60 |
+
|
61 |
+
```
|
62 |
+
|
63 |
+
## Model file specification
|
64 |
+
|
65 |
+
| Filename | Quant type | File Size | Description |
|
66 |
+
| -------- | ---------- | --------- | ----------- |
|
67 |
+
| [speechless-coding-7b-16k-tora-Q2_K.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
|
68 |
+
| [speechless-coding-7b-16k-tora-Q3_K_S.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q3_K_S.gguf) | Q3_K_S | 2.948 GB | very small, high quality loss |
|
69 |
+
| [speechless-coding-7b-16k-tora-Q3_K_M.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q3_K_M.gguf) | Q3_K_M | 3.298 GB | very small, high quality loss |
|
70 |
+
| [speechless-coding-7b-16k-tora-Q3_K_L.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q3_K_L.gguf) | Q3_K_L | 3.597 GB | small, substantial quality loss |
|
71 |
+
| [speechless-coding-7b-16k-tora-Q4_0.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q4_0.gguf) | Q4_0 | 3.826 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
72 |
+
| [speechless-coding-7b-16k-tora-Q4_K_S.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q4_K_S.gguf) | Q4_K_S | 3.857 GB | small, greater quality loss |
|
73 |
+
| [speechless-coding-7b-16k-tora-Q4_K_M.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q4_K_M.gguf) | Q4_K_M | 4.081 GB | medium, balanced quality - recommended |
|
74 |
+
| [speechless-coding-7b-16k-tora-Q5_0.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q5_0.gguf) | Q5_0 | 4.652 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
75 |
+
| [speechless-coding-7b-16k-tora-Q5_K_S.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q5_K_S.gguf) | Q5_K_S | 4.652 GB | large, low quality loss - recommended |
|
76 |
+
| [speechless-coding-7b-16k-tora-Q5_K_M.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q5_K_M.gguf) | Q5_K_M | 4.783 GB | large, very low quality loss - recommended |
|
77 |
+
| [speechless-coding-7b-16k-tora-Q6_K.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q6_K.gguf) | Q6_K | 5.529 GB | very large, extremely low quality loss |
|
78 |
+
| [speechless-coding-7b-16k-tora-Q8_0.gguf](https://huggingface.co/tensorblock/speechless-coding-7b-16k-tora-GGUF/blob/main/speechless-coding-7b-16k-tora-Q8_0.gguf) | Q8_0 | 7.161 GB | very large, extremely low quality loss - not recommended |
|
79 |
+
|
80 |
+
|
81 |
+
## Downloading instruction
|
82 |
+
|
83 |
+
### Command line
|
84 |
+
|
85 |
+
Firstly, install Huggingface Client
|
86 |
+
|
87 |
+
```shell
|
88 |
+
pip install -U "huggingface_hub[cli]"
|
89 |
+
```
|
90 |
+
|
91 |
+
Then, downoad the individual model file the a local directory
|
92 |
+
|
93 |
+
```shell
|
94 |
+
huggingface-cli download tensorblock/speechless-coding-7b-16k-tora-GGUF --include "speechless-coding-7b-16k-tora-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
95 |
+
```
|
96 |
+
|
97 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
98 |
+
|
99 |
+
```shell
|
100 |
+
huggingface-cli download tensorblock/speechless-coding-7b-16k-tora-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
101 |
+
```
|
speechless-coding-7b-16k-tora-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd7816058167d2ea41cfdc0527a8bd95760d4d63bdb69a483ce0e8d662687720
|
3 |
+
size 2532870208
|
speechless-coding-7b-16k-tora-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16d909f46b0cd1b2a92bf9c1615850a97f540a90dc7f5764374d842f96dbfa3c
|
3 |
+
size 3597117920
|
speechless-coding-7b-16k-tora-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44b713550104605be610d401ce76c36a2a7766f96b3bee65282bdc90306c4860
|
3 |
+
size 3298011616
|
speechless-coding-7b-16k-tora-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f767d67fa86fdb4ead4cdad37794f522c02a319145c5f5681107fb862b5ee74
|
3 |
+
size 2948311520
|
speechless-coding-7b-16k-tora-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4b5a51af0f32934f1e3d0a6f548fdf8dcdaf021a9639aa43174dbf2a0ab095b
|
3 |
+
size 3825814528
|
speechless-coding-7b-16k-tora-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:055eba7fbc1f3fe1b325aa645e6715039d6933e5af53092aa3a3bc4cb62f4ea4
|
3 |
+
size 4081011712
|
speechless-coding-7b-16k-tora-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa9400e5116911c22af451b41a57a8b666e1fafea45fe53fd032c608bc9d7ba1
|
3 |
+
size 3856747520
|
speechless-coding-7b-16k-tora-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f69222740606af4dea39172eebe5ebe08948fe51f0f4af60138620324381188b
|
3 |
+
size 4651699712
|
speechless-coding-7b-16k-tora-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e492d3a2f32807a0a4d7547420395009e19bfda2955eb26064a34de4950bd70
|
3 |
+
size 4783164928
|
speechless-coding-7b-16k-tora-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efc2b6ae41c49af64cb58ac4eb94d10e24a04f785c08f0c9f9a49e1c0ed7ce4d
|
3 |
+
size 4651699712
|
speechless-coding-7b-16k-tora-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b95c4438c0b76c958b26b5e07a91411e2a2efb52bf53b0e27a6e8ae346aff47d
|
3 |
+
size 5529202720
|
speechless-coding-7b-16k-tora-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:712876c0787af25afbeaa6164a405acd6442317b3d3f375b97cda5c5be8f974a
|
3 |
+
size 7161100256
|