Update README.md
Browse files
README.md
CHANGED
|
@@ -29,8 +29,16 @@ This repo contains GGUF format model files for [Qwen/Qwen1.5-MoE-A2.7B-Chat](htt
|
|
| 29 |
|
| 30 |
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).
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
## Prompt template
|
| 33 |
|
|
|
|
| 34 |
```
|
| 35 |
<|im_start|>system
|
| 36 |
{system_prompt}<|im_end|>
|
|
@@ -43,18 +51,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 43 |
|
| 44 |
| Filename | Quant type | File Size | Description |
|
| 45 |
| -------- | ---------- | --------- | ----------- |
|
| 46 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 47 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 48 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 49 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 50 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 51 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 52 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 53 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 54 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 55 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 56 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 57 |
-
| [Qwen1.5-MoE-A2.7B-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/
|
| 58 |
|
| 59 |
|
| 60 |
## Downloading instruction
|
|
|
|
| 29 |
|
| 30 |
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).
|
| 31 |
|
| 32 |
+
|
| 33 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 34 |
+
<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;">
|
| 35 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 36 |
+
</a>
|
| 37 |
+
</div>
|
| 38 |
+
|
| 39 |
## Prompt template
|
| 40 |
|
| 41 |
+
|
| 42 |
```
|
| 43 |
<|im_start|>system
|
| 44 |
{system_prompt}<|im_end|>
|
|
|
|
| 51 |
|
| 52 |
| Filename | Quant type | File Size | Description |
|
| 53 |
| -------- | ---------- | --------- | ----------- |
|
| 54 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q2_K.gguf) | Q2_K | 5.486 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 55 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q3_K_S.gguf) | Q3_K_S | 6.372 GB | very small, high quality loss |
|
| 56 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q3_K_M.gguf) | Q3_K_M | 6.927 GB | very small, high quality loss |
|
| 57 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q3_K_L.gguf) | Q3_K_L | 7.212 GB | small, substantial quality loss |
|
| 58 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q4_0.gguf) | Q4_0 | 7.590 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 59 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q4_K_S.gguf) | Q4_K_S | 8.110 GB | small, greater quality loss |
|
| 60 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q4_K_M.gguf) | Q4_K_M | 8.844 GB | medium, balanced quality - recommended |
|
| 61 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q5_0.gguf) | Q5_0 | 9.220 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 62 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q5_K_S.gguf) | Q5_K_S | 9.462 GB | large, low quality loss - recommended |
|
| 63 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q5_K_M.gguf) | Q5_K_M | 10.090 GB | large, very low quality loss - recommended |
|
| 64 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q6_K.gguf) | Q6_K | 11.889 GB | very large, extremely low quality loss |
|
| 65 |
+
| [Qwen1.5-MoE-A2.7B-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-MoE-A2.7B-Chat-GGUF/blob/main/Qwen1.5-MoE-A2.7B-Chat-Q8_0.gguf) | Q8_0 | 14.180 GB | very large, extremely low quality loss - not recommended |
|
| 66 |
|
| 67 |
|
| 68 |
## Downloading instruction
|