Update README.md
Browse files
README.md
CHANGED
@@ -12,11 +12,11 @@ tags:
|
|
12 |
quantized_by: bartowski
|
13 |
---
|
14 |
|
15 |
-
## Llamacpp imatrix Quantizations of ChatQA-1.5-8B
|
16 |
|
17 |
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2777">b2777</a> for quantization.
|
18 |
|
19 |
-
Original model: https://huggingface.co/nvidia/ChatQA-1.5-8B
|
20 |
|
21 |
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
|
22 |
|
@@ -41,28 +41,28 @@ Assistant:
|
|
41 |
|
42 |
| Filename | Quant type | File Size | Description |
|
43 |
| -------- | ---------- | --------- | ----------- |
|
44 |
-
| [ChatQA-1.5-8B-Q8_0.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
|
45 |
-
| [ChatQA-1.5-8B-Q6_K.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
|
46 |
-
| [ChatQA-1.5-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
|
47 |
-
| [ChatQA-1.5-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
|
48 |
-
| [ChatQA-1.5-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
|
49 |
-
| [ChatQA-1.5-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
|
50 |
-
| [ChatQA-1.5-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
|
51 |
-
| [ChatQA-1.5-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
52 |
-
| [ChatQA-1.5-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
|
53 |
-
| [ChatQA-1.5-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
|
54 |
-
| [ChatQA-1.5-8B-IQ3_M.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
55 |
-
| [ChatQA-1.5-8B-IQ3_S.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
|
56 |
-
| [ChatQA-1.5-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
|
57 |
-
| [ChatQA-1.5-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
58 |
-
| [ChatQA-1.5-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
59 |
-
| [ChatQA-1.5-8B-Q2_K.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
|
60 |
-
| [ChatQA-1.5-8B-IQ2_M.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
|
61 |
-
| [ChatQA-1.5-8B-IQ2_S.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
|
62 |
-
| [ChatQA-1.5-8B-IQ2_XS.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
|
63 |
-
| [ChatQA-1.5-8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
|
64 |
-
| [ChatQA-1.5-8B-IQ1_M.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
|
65 |
-
| [ChatQA-1.5-8B-IQ1_S.gguf](https://huggingface.co/bartowski/ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
|
66 |
|
67 |
## Which file should I choose?
|
68 |
|
|
|
12 |
quantized_by: bartowski
|
13 |
---
|
14 |
|
15 |
+
## Llamacpp imatrix Quantizations of Llama-3-ChatQA-1.5-8B
|
16 |
|
17 |
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2777">b2777</a> for quantization.
|
18 |
|
19 |
+
Original model: https://huggingface.co/nvidia/Llama-3-ChatQA-1.5-8B
|
20 |
|
21 |
All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
|
22 |
|
|
|
41 |
|
42 |
| Filename | Quant type | File Size | Description |
|
43 |
| -------- | ---------- | --------- | ----------- |
|
44 |
+
| [ChatQA-1.5-8B-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. |
|
45 |
+
| [ChatQA-1.5-8B-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. |
|
46 |
+
| [ChatQA-1.5-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. |
|
47 |
+
| [ChatQA-1.5-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. |
|
48 |
+
| [ChatQA-1.5-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
|
49 |
+
| [ChatQA-1.5-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. |
|
50 |
+
| [ChatQA-1.5-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
|
51 |
+
| [ChatQA-1.5-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
52 |
+
| [ChatQA-1.5-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. |
|
53 |
+
| [ChatQA-1.5-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. |
|
54 |
+
| [ChatQA-1.5-8B-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
55 |
+
| [ChatQA-1.5-8B-IQ3_S.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
|
56 |
+
| [ChatQA-1.5-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. |
|
57 |
+
| [ChatQA-1.5-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
58 |
+
| [ChatQA-1.5-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
59 |
+
| [ChatQA-1.5-8B-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. |
|
60 |
+
| [ChatQA-1.5-8B-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
|
61 |
+
| [ChatQA-1.5-8B-IQ2_S.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. |
|
62 |
+
| [ChatQA-1.5-8B-IQ2_XS.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. |
|
63 |
+
| [ChatQA-1.5-8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. |
|
64 |
+
| [ChatQA-1.5-8B-IQ1_M.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. |
|
65 |
+
| [ChatQA-1.5-8B-IQ1_S.gguf](https://huggingface.co/bartowski/Llama-3-ChatQA-1.5-8B-GGUF/blob/main/ChatQA-1.5-8B-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. |
|
66 |
|
67 |
## Which file should I choose?
|
68 |
|