Instructions to use tensorblock/33x-coder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tensorblock/33x-coder-GGUF with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tensorblock/33x-coder-GGUF", dtype="auto") - llama-cpp-python
How to use tensorblock/33x-coder-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="tensorblock/33x-coder-GGUF", filename="33x-coder-Q2_K.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use tensorblock/33x-coder-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf tensorblock/33x-coder-GGUF:Q2_K # Run inference directly in the terminal: llama-cli -hf tensorblock/33x-coder-GGUF:Q2_K
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf tensorblock/33x-coder-GGUF:Q2_K # Run inference directly in the terminal: llama-cli -hf tensorblock/33x-coder-GGUF:Q2_K
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf tensorblock/33x-coder-GGUF:Q2_K # Run inference directly in the terminal: ./llama-cli -hf tensorblock/33x-coder-GGUF:Q2_K
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf tensorblock/33x-coder-GGUF:Q2_K # Run inference directly in the terminal: ./build/bin/llama-cli -hf tensorblock/33x-coder-GGUF:Q2_K
Use Docker
docker model run hf.co/tensorblock/33x-coder-GGUF:Q2_K
- LM Studio
- Jan
- Ollama
How to use tensorblock/33x-coder-GGUF with Ollama:
ollama run hf.co/tensorblock/33x-coder-GGUF:Q2_K
- Unsloth Studio new
How to use tensorblock/33x-coder-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tensorblock/33x-coder-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tensorblock/33x-coder-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tensorblock/33x-coder-GGUF to start chatting
- Docker Model Runner
How to use tensorblock/33x-coder-GGUF with Docker Model Runner:
docker model run hf.co/tensorblock/33x-coder-GGUF:Q2_K
- Lemonade
How to use tensorblock/33x-coder-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tensorblock/33x-coder-GGUF:Q2_K
Run and chat with the model
lemonade run user.33x-coder-GGUF-Q2_K
List all available models
lemonade list
Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- 33x-coder-Q2_K.gguf +3 -0
- 33x-coder-Q3_K_L.gguf +3 -0
- 33x-coder-Q3_K_M.gguf +3 -0
- 33x-coder-Q3_K_S.gguf +3 -0
- 33x-coder-Q4_0.gguf +3 -0
- 33x-coder-Q4_K_M.gguf +3 -0
- 33x-coder-Q4_K_S.gguf +3 -0
- 33x-coder-Q5_0.gguf +3 -0
- 33x-coder-Q5_K_M.gguf +3 -0
- 33x-coder-Q5_K_S.gguf +3 -0
- 33x-coder-Q6_K.gguf +3 -0
- 33x-coder-Q8_0.gguf +3 -0
- README.md +85 -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 |
+
33x-coder-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
33x-coder-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
33x-coder-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
33x-coder-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
33x-coder-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
33x-coder-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
33x-coder-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
33x-coder-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
33x-coder-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
33x-coder-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
33x-coder-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
33x-coder-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
33x-coder-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85d66080f82f722bcc30b6e434074279d5d4f5315e4291dcfb1af210b0a7044f
|
| 3 |
+
size 12355754528
|
33x-coder-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cb29de31b609ff4cfc6968ae0e3a49762fe39754455d6dd5293af4828216b5f
|
| 3 |
+
size 17560238624
|
33x-coder-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:948d9e7cbac37b08f116dcb753cdc6ceb403cf7a662669a92efbed3e4a81471f
|
| 3 |
+
size 16092002848
|
33x-coder-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c3e2e9e40dd8a4030370cb0d4ac7700a5939d2425be4332a43b1c906260881a
|
| 3 |
+
size 14421772832
|
33x-coder-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2d68932b5de2f7206d8985baf5c6563632e3d23d3eedd8bfc53fb15accb1436
|
| 3 |
+
size 18819312160
|
33x-coder-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05e50a14505bc7c6e2a34dc98e7eeaca5c81d97d72121e77e72ad3f6ac4d8383
|
| 3 |
+
size 19940530720
|
33x-coder-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:222477fc1ab5b693899f4331938bffa89e6aca0eacdb97773c266a48fafd42df
|
| 3 |
+
size 18943404576
|
33x-coder-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4af0befafce467fae6eec93381ddcb4a787a58f3da9b2ed92fdc6bddf643301e
|
| 3 |
+
size 22958172704
|
33x-coder-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:980c02eebb0f621c699c54a6363649d81d8329a91a6bcb43255dcc79cc9cc93c
|
| 3 |
+
size 23535770144
|
33x-coder-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07c4468f55c97feb71d7301f20c76eb3f0c2d6629b57f73421d9f44b8c0d1edf
|
| 3 |
+
size 22958172704
|
33x-coder-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:113715d2d7c6efee22885948e0e493d2e6764be2b4fb219fcd802a9fe6757316
|
| 3 |
+
size 27355712032
|
33x-coder-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8361c62cbe454dac9ffc5a19df30347dfc2d4e2f08f0c3f3536d34666624ddd2
|
| 3 |
+
size 35430750752
|
README.md
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
metrics:
|
| 5 |
+
- code_eval
|
| 6 |
+
library_name: transformers
|
| 7 |
+
tags:
|
| 8 |
+
- Code Generation
|
| 9 |
+
- TensorBlock
|
| 10 |
+
- GGUF
|
| 11 |
+
datasets:
|
| 12 |
+
- andersonbcdefg/synthetic_retrieval_tasks
|
| 13 |
+
- ise-uiuc/Magicoder-Evol-Instruct-110K
|
| 14 |
+
license: apache-2.0
|
| 15 |
+
base_model: senseable/33x-coder
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 19 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 20 |
+
</div>
|
| 21 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
| 22 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
| 23 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
| 24 |
+
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>
|
| 25 |
+
</p>
|
| 26 |
+
</div>
|
| 27 |
+
</div>
|
| 28 |
+
|
| 29 |
+
## senseable/33x-coder - GGUF
|
| 30 |
+
|
| 31 |
+
This repo contains GGUF format model files for [senseable/33x-coder](https://huggingface.co/senseable/33x-coder).
|
| 32 |
+
|
| 33 |
+
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).
|
| 34 |
+
|
| 35 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 36 |
+
<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;">
|
| 37 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 38 |
+
</a>
|
| 39 |
+
</div>
|
| 40 |
+
|
| 41 |
+
## Prompt template
|
| 42 |
+
|
| 43 |
+
```
|
| 44 |
+
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
## Model file specification
|
| 48 |
+
|
| 49 |
+
| Filename | Quant type | File Size | Description |
|
| 50 |
+
| -------- | ---------- | --------- | ----------- |
|
| 51 |
+
| [33x-coder-Q2_K.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q2_K.gguf) | Q2_K | 12.356 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 52 |
+
| [33x-coder-Q3_K_S.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q3_K_S.gguf) | Q3_K_S | 14.422 GB | very small, high quality loss |
|
| 53 |
+
| [33x-coder-Q3_K_M.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q3_K_M.gguf) | Q3_K_M | 16.092 GB | very small, high quality loss |
|
| 54 |
+
| [33x-coder-Q3_K_L.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q3_K_L.gguf) | Q3_K_L | 17.560 GB | small, substantial quality loss |
|
| 55 |
+
| [33x-coder-Q4_0.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q4_0.gguf) | Q4_0 | 18.819 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 56 |
+
| [33x-coder-Q4_K_S.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q4_K_S.gguf) | Q4_K_S | 18.943 GB | small, greater quality loss |
|
| 57 |
+
| [33x-coder-Q4_K_M.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q4_K_M.gguf) | Q4_K_M | 19.941 GB | medium, balanced quality - recommended |
|
| 58 |
+
| [33x-coder-Q5_0.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q5_0.gguf) | Q5_0 | 22.958 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 59 |
+
| [33x-coder-Q5_K_S.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q5_K_S.gguf) | Q5_K_S | 22.958 GB | large, low quality loss - recommended |
|
| 60 |
+
| [33x-coder-Q5_K_M.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q5_K_M.gguf) | Q5_K_M | 23.536 GB | large, very low quality loss - recommended |
|
| 61 |
+
| [33x-coder-Q6_K.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q6_K.gguf) | Q6_K | 27.356 GB | very large, extremely low quality loss |
|
| 62 |
+
| [33x-coder-Q8_0.gguf](https://huggingface.co/tensorblock/33x-coder-GGUF/blob/main/33x-coder-Q8_0.gguf) | Q8_0 | 35.431 GB | very large, extremely low quality loss - not recommended |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
## Downloading instruction
|
| 66 |
+
|
| 67 |
+
### Command line
|
| 68 |
+
|
| 69 |
+
Firstly, install Huggingface Client
|
| 70 |
+
|
| 71 |
+
```shell
|
| 72 |
+
pip install -U "huggingface_hub[cli]"
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
Then, downoad the individual model file the a local directory
|
| 76 |
+
|
| 77 |
+
```shell
|
| 78 |
+
huggingface-cli download tensorblock/33x-coder-GGUF --include "33x-coder-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
| 82 |
+
|
| 83 |
+
```shell
|
| 84 |
+
huggingface-cli download tensorblock/33x-coder-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
| 85 |
+
```
|