morriszms commited on
Commit
ce54ba7
·
verified ·
1 Parent(s): 824dd2f

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +12 -14
README.md CHANGED
@@ -29,7 +29,6 @@ This repo contains GGUF format model files for [Qwen/Qwen1.5-1.8B](https://huggi
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 ↗
@@ -38,7 +37,6 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
38
 
39
  ## Prompt template
40
 
41
-
42
  ```
43
  <|im_start|>system
44
  {system_prompt}<|im_end|>
@@ -51,18 +49,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
51
 
52
  | Filename | Quant type | File Size | Description |
53
  | -------- | ---------- | --------- | ----------- |
54
- | [Qwen1.5-1.8B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q2_K.gguf) | Q2_K | 0.788 GB | smallest, significant quality loss - not recommended for most purposes |
55
- | [Qwen1.5-1.8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q3_K_S.gguf) | Q3_K_S | 0.888 GB | very small, high quality loss |
56
- | [Qwen1.5-1.8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q3_K_M.gguf) | Q3_K_M | 0.946 GB | very small, high quality loss |
57
- | [Qwen1.5-1.8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q3_K_L.gguf) | Q3_K_L | 0.984 GB | small, substantial quality loss |
58
- | [Qwen1.5-1.8B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q4_0.gguf) | Q4_0 | 1.043 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
59
- | [Qwen1.5-1.8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q4_K_S.gguf) | Q4_K_S | 1.079 GB | small, greater quality loss |
60
- | [Qwen1.5-1.8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q4_K_M.gguf) | Q4_K_M | 1.134 GB | medium, balanced quality - recommended |
61
- | [Qwen1.5-1.8B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q5_0.gguf) | Q5_0 | 1.221 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
62
- | [Qwen1.5-1.8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q5_K_S.gguf) | Q5_K_S | 1.237 GB | large, low quality loss - recommended |
63
- | [Qwen1.5-1.8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q5_K_M.gguf) | Q5_K_M | 1.282 GB | large, very low quality loss - recommended |
64
- | [Qwen1.5-1.8B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q6_K.gguf) | Q6_K | 1.471 GB | very large, extremely low quality loss |
65
- | [Qwen1.5-1.8B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q8_0.gguf) | Q8_0 | 1.824 GB | very large, extremely low quality loss - not recommended |
66
 
67
 
68
  ## 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
  <div style="text-align: left; margin: 20px 0;">
33
  <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;">
34
  Run them on the TensorBlock client using your local machine ↗
 
37
 
38
  ## Prompt template
39
 
 
40
  ```
41
  <|im_start|>system
42
  {system_prompt}<|im_end|>
 
49
 
50
  | Filename | Quant type | File Size | Description |
51
  | -------- | ---------- | --------- | ----------- |
52
+ | [Qwen1.5-1.8B-Q2_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q2_K.gguf) | Q2_K | 0.847 GB | smallest, significant quality loss - not recommended for most purposes |
53
+ | [Qwen1.5-1.8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q3_K_S.gguf) | Q3_K_S | 0.954 GB | very small, high quality loss |
54
+ | [Qwen1.5-1.8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q3_K_M.gguf) | Q3_K_M | 1.016 GB | very small, high quality loss |
55
+ | [Qwen1.5-1.8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q3_K_L.gguf) | Q3_K_L | 1.056 GB | small, substantial quality loss |
56
+ | [Qwen1.5-1.8B-Q4_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q4_0.gguf) | Q4_0 | 1.120 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
57
+ | [Qwen1.5-1.8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q4_K_S.gguf) | Q4_K_S | 1.158 GB | small, greater quality loss |
58
+ | [Qwen1.5-1.8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q4_K_M.gguf) | Q4_K_M | 1.218 GB | medium, balanced quality - recommended |
59
+ | [Qwen1.5-1.8B-Q5_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q5_0.gguf) | Q5_0 | 1.311 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
60
+ | [Qwen1.5-1.8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q5_K_S.gguf) | Q5_K_S | 1.328 GB | large, low quality loss - recommended |
61
+ | [Qwen1.5-1.8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q5_K_M.gguf) | Q5_K_M | 1.377 GB | large, very low quality loss - recommended |
62
+ | [Qwen1.5-1.8B-Q6_K.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q6_K.gguf) | Q6_K | 1.579 GB | very large, extremely low quality loss |
63
+ | [Qwen1.5-1.8B-Q8_0.gguf](https://huggingface.co/tensorblock/Qwen1.5-1.8B-GGUF/blob/main/Qwen1.5-1.8B-Q8_0.gguf) | Q8_0 | 1.958 GB | very large, extremely low quality loss - not recommended |
64
 
65
 
66
  ## Downloading instruction