Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +100 -0
- speechless-codellama-34b-v1.9-Q2_K.gguf +3 -0
- speechless-codellama-34b-v1.9-Q3_K_L.gguf +3 -0
- speechless-codellama-34b-v1.9-Q3_K_M.gguf +3 -0
- speechless-codellama-34b-v1.9-Q3_K_S.gguf +3 -0
- speechless-codellama-34b-v1.9-Q4_0.gguf +3 -0
- speechless-codellama-34b-v1.9-Q4_K_M.gguf +3 -0
- speechless-codellama-34b-v1.9-Q4_K_S.gguf +3 -0
- speechless-codellama-34b-v1.9-Q5_0.gguf +3 -0
- speechless-codellama-34b-v1.9-Q5_K_M.gguf +3 -0
- speechless-codellama-34b-v1.9-Q5_K_S.gguf +3 -0
- speechless-codellama-34b-v1.9-Q6_K.gguf +3 -0
- speechless-codellama-34b-v1.9-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-codellama-34b-v1.9-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
speechless-codellama-34b-v1.9-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
speechless-codellama-34b-v1.9-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
speechless-codellama-34b-v1.9-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
speechless-codellama-34b-v1.9-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
speechless-codellama-34b-v1.9-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
speechless-codellama-34b-v1.9-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
speechless-codellama-34b-v1.9-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
speechless-codellama-34b-v1.9-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
speechless-codellama-34b-v1.9-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
speechless-codellama-34b-v1.9-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
speechless-codellama-34b-v1.9-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
tags:
|
12 |
+
- llama-2
|
13 |
+
- code
|
14 |
+
- TensorBlock
|
15 |
+
- GGUF
|
16 |
+
license: llama2
|
17 |
+
base_model: uukuguy/speechless-codellama-34b-v1.9
|
18 |
+
model-index:
|
19 |
+
- name: SpeechlessCoder
|
20 |
+
results:
|
21 |
+
- task:
|
22 |
+
type: text-generation
|
23 |
+
dataset:
|
24 |
+
name: HumanEval
|
25 |
+
type: openai_humaneval
|
26 |
+
metrics:
|
27 |
+
- type: pass@1
|
28 |
+
value: 70.73
|
29 |
+
name: pass@1
|
30 |
+
verified: false
|
31 |
+
---
|
32 |
+
|
33 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
34 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
35 |
+
</div>
|
36 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
37 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
38 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
39 |
+
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>
|
40 |
+
</p>
|
41 |
+
</div>
|
42 |
+
</div>
|
43 |
+
|
44 |
+
## uukuguy/speechless-codellama-34b-v1.9 - GGUF
|
45 |
+
|
46 |
+
This repo contains GGUF format model files for [uukuguy/speechless-codellama-34b-v1.9](https://huggingface.co/uukuguy/speechless-codellama-34b-v1.9).
|
47 |
+
|
48 |
+
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).
|
49 |
+
|
50 |
+
<div style="text-align: left; margin: 20px 0;">
|
51 |
+
<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;">
|
52 |
+
Run them on the TensorBlock client using your local machine ↗
|
53 |
+
</a>
|
54 |
+
</div>
|
55 |
+
|
56 |
+
## Prompt template
|
57 |
+
|
58 |
+
```
|
59 |
+
|
60 |
+
```
|
61 |
+
|
62 |
+
## Model file specification
|
63 |
+
|
64 |
+
| Filename | Quant type | File Size | Description |
|
65 |
+
| -------- | ---------- | --------- | ----------- |
|
66 |
+
| [speechless-codellama-34b-v1.9-Q2_K.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q2_K.gguf) | Q2_K | 12.506 GB | smallest, significant quality loss - not recommended for most purposes |
|
67 |
+
| [speechless-codellama-34b-v1.9-Q3_K_S.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q3_K_S.gguf) | Q3_K_S | 14.605 GB | very small, high quality loss |
|
68 |
+
| [speechless-codellama-34b-v1.9-Q3_K_M.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q3_K_M.gguf) | Q3_K_M | 16.306 GB | very small, high quality loss |
|
69 |
+
| [speechless-codellama-34b-v1.9-Q3_K_L.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q3_K_L.gguf) | Q3_K_L | 17.772 GB | small, substantial quality loss |
|
70 |
+
| [speechless-codellama-34b-v1.9-Q4_0.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q4_0.gguf) | Q4_0 | 19.052 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
71 |
+
| [speechless-codellama-34b-v1.9-Q4_K_S.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q4_K_S.gguf) | Q4_K_S | 19.192 GB | small, greater quality loss |
|
72 |
+
| [speechless-codellama-34b-v1.9-Q4_K_M.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q4_K_M.gguf) | Q4_K_M | 20.220 GB | medium, balanced quality - recommended |
|
73 |
+
| [speechless-codellama-34b-v1.9-Q5_0.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q5_0.gguf) | Q5_0 | 23.237 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
74 |
+
| [speechless-codellama-34b-v1.9-Q5_K_S.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q5_K_S.gguf) | Q5_K_S | 23.237 GB | large, low quality loss - recommended |
|
75 |
+
| [speechless-codellama-34b-v1.9-Q5_K_M.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q5_K_M.gguf) | Q5_K_M | 23.839 GB | large, very low quality loss - recommended |
|
76 |
+
| [speechless-codellama-34b-v1.9-Q6_K.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q6_K.gguf) | Q6_K | 27.684 GB | very large, extremely low quality loss |
|
77 |
+
| [speechless-codellama-34b-v1.9-Q8_0.gguf](https://huggingface.co/tensorblock/speechless-codellama-34b-v1.9-GGUF/blob/main/speechless-codellama-34b-v1.9-Q8_0.gguf) | Q8_0 | 35.856 GB | very large, extremely low quality loss - not recommended |
|
78 |
+
|
79 |
+
|
80 |
+
## Downloading instruction
|
81 |
+
|
82 |
+
### Command line
|
83 |
+
|
84 |
+
Firstly, install Huggingface Client
|
85 |
+
|
86 |
+
```shell
|
87 |
+
pip install -U "huggingface_hub[cli]"
|
88 |
+
```
|
89 |
+
|
90 |
+
Then, downoad the individual model file the a local directory
|
91 |
+
|
92 |
+
```shell
|
93 |
+
huggingface-cli download tensorblock/speechless-codellama-34b-v1.9-GGUF --include "speechless-codellama-34b-v1.9-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
94 |
+
```
|
95 |
+
|
96 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
97 |
+
|
98 |
+
```shell
|
99 |
+
huggingface-cli download tensorblock/speechless-codellama-34b-v1.9-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
100 |
+
```
|
speechless-codellama-34b-v1.9-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:558b8efb59bb657ba22c154bd92c887f972bfcf0f03cb74702772489e0e716fa
|
3 |
+
size 12505691712
|
speechless-codellama-34b-v1.9-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4e09c9d6028dbbbba28df01d48524dd657647f173ebb7d8e20e367fa2dba6c5
|
3 |
+
size 17771525696
|
speechless-codellama-34b-v1.9-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b892419be012a4d7ce6874e7c21deceb529f51ef7f8bd359ae46366d6dbb373d
|
3 |
+
size 16306140736
|
speechless-codellama-34b-v1.9-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2457fce132461faa828cd66f2cbb1dbf37a9c5d4f9fb84455f6fd32174b2659
|
3 |
+
size 14605350464
|
speechless-codellama-34b-v1.9-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18da2851aa1ddfdc61ad75fa7750b37ba60b89a0960c86e47ce2ef29740d19ee
|
3 |
+
size 19052049984
|
speechless-codellama-34b-v1.9-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:660f717a1fd899f59bad8faa261a7f941129f94f81c50f3410e6c813e47d9c3e
|
3 |
+
size 20219901504
|
speechless-codellama-34b-v1.9-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb163e0300fe5c7d1ff42568706e81b48858801b7eb6b67812f16adbbcaadac9
|
3 |
+
size 19191510592
|
speechless-codellama-34b-v1.9-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1ab276fbfaf4404b6eeb0d89b066d2f816b0100093212a9f57ae1352da76777
|
3 |
+
size 23237178944
|
speechless-codellama-34b-v1.9-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09393023ba0d756d88091777a23a8b7352bdc342de39f3a134bd41b177450d27
|
3 |
+
size 23838799424
|
speechless-codellama-34b-v1.9-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6814fa019cc42c4099045b045ddffc5b2cf7b8397a71e2e445131e92a91383e9
|
3 |
+
size 23237178944
|
speechless-codellama-34b-v1.9-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4aa69f2f7b98fe59324f1aeeac48561b7b8bf7f5d38c3e746fdb4fdcd966e82
|
3 |
+
size 27683878464
|
speechless-codellama-34b-v1.9-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0e45ece9f23c1f0125b254ed679b6d07e42cdaedbec197f0f5a465871f9af2e
|
3 |
+
size 35856053824
|