Update README.md
Browse files
README.md
CHANGED
|
@@ -27,8 +27,16 @@ This repo contains GGUF format model files for [m-a-p/OpenCodeInterpreter-DS-6.7
|
|
| 27 |
|
| 28 |
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).
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
## Prompt template
|
| 31 |
|
|
|
|
| 32 |
```
|
| 33 |
You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.
|
| 34 |
{system_prompt}### Instruction:
|
|
@@ -40,18 +48,18 @@ You are an AI programming assistant, utilizing the Deepseek Coder model, develop
|
|
| 40 |
|
| 41 |
| Filename | Quant type | File Size | Description |
|
| 42 |
| -------- | ---------- | --------- | ----------- |
|
| 43 |
-
| [OpenCodeInterpreter-DS-6.7B-Q2_K.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 44 |
-
| [OpenCodeInterpreter-DS-6.7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 45 |
-
| [OpenCodeInterpreter-DS-6.7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 46 |
-
| [OpenCodeInterpreter-DS-6.7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 47 |
-
| [OpenCodeInterpreter-DS-6.7B-Q4_0.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 48 |
-
| [OpenCodeInterpreter-DS-6.7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 49 |
-
| [OpenCodeInterpreter-DS-6.7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 50 |
-
| [OpenCodeInterpreter-DS-6.7B-Q5_0.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 51 |
-
| [OpenCodeInterpreter-DS-6.7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 52 |
-
| [OpenCodeInterpreter-DS-6.7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 53 |
-
| [OpenCodeInterpreter-DS-6.7B-Q6_K.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 54 |
-
| [OpenCodeInterpreter-DS-6.7B-Q8_0.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/
|
| 55 |
|
| 56 |
|
| 57 |
## Downloading instruction
|
|
|
|
| 27 |
|
| 28 |
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).
|
| 29 |
|
| 30 |
+
|
| 31 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 32 |
+
<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;">
|
| 33 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 34 |
+
</a>
|
| 35 |
+
</div>
|
| 36 |
+
|
| 37 |
## Prompt template
|
| 38 |
|
| 39 |
+
|
| 40 |
```
|
| 41 |
You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.
|
| 42 |
{system_prompt}### Instruction:
|
|
|
|
| 48 |
|
| 49 |
| Filename | Quant type | File Size | Description |
|
| 50 |
| -------- | ---------- | --------- | ----------- |
|
| 51 |
+
| [OpenCodeInterpreter-DS-6.7B-Q2_K.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q2_K.gguf) | Q2_K | 2.360 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 52 |
+
| [OpenCodeInterpreter-DS-6.7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q3_K_S.gguf) | Q3_K_S | 2.747 GB | very small, high quality loss |
|
| 53 |
+
| [OpenCodeInterpreter-DS-6.7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q3_K_M.gguf) | Q3_K_M | 3.073 GB | very small, high quality loss |
|
| 54 |
+
| [OpenCodeInterpreter-DS-6.7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q3_K_L.gguf) | Q3_K_L | 3.352 GB | small, substantial quality loss |
|
| 55 |
+
| [OpenCodeInterpreter-DS-6.7B-Q4_0.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q4_0.gguf) | Q4_0 | 3.565 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 56 |
+
| [OpenCodeInterpreter-DS-6.7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q4_K_S.gguf) | Q4_K_S | 3.594 GB | small, greater quality loss |
|
| 57 |
+
| [OpenCodeInterpreter-DS-6.7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q4_K_M.gguf) | Q4_K_M | 3.802 GB | medium, balanced quality - recommended |
|
| 58 |
+
| [OpenCodeInterpreter-DS-6.7B-Q5_0.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q5_0.gguf) | Q5_0 | 4.334 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 59 |
+
| [OpenCodeInterpreter-DS-6.7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q5_K_S.gguf) | Q5_K_S | 4.334 GB | large, low quality loss - recommended |
|
| 60 |
+
| [OpenCodeInterpreter-DS-6.7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q5_K_M.gguf) | Q5_K_M | 4.457 GB | large, very low quality loss - recommended |
|
| 61 |
+
| [OpenCodeInterpreter-DS-6.7B-Q6_K.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q6_K.gguf) | Q6_K | 5.151 GB | very large, extremely low quality loss |
|
| 62 |
+
| [OpenCodeInterpreter-DS-6.7B-Q8_0.gguf](https://huggingface.co/tensorblock/OpenCodeInterpreter-DS-6.7B-GGUF/blob/main/OpenCodeInterpreter-DS-6.7B-Q8_0.gguf) | Q8_0 | 6.672 GB | very large, extremely low quality loss - not recommended |
|
| 63 |
|
| 64 |
|
| 65 |
## Downloading instruction
|