Initial GGML model commit
Browse files
README.md
CHANGED
|
@@ -76,7 +76,18 @@ Refer to the Provided Files table below to see what files use which methods, and
|
|
| 76 |
## Provided files
|
| 77 |
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
| 78 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
| 79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
|
| 82 |
|
|
|
|
| 76 |
## Provided files
|
| 77 |
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|
| 78 |
| ---- | ---- | ---- | ---- | ---- | ----- |
|
| 79 |
+
| llama-65b.ggmlv3.q2_K.bin | q2_K | 2 | 27.33 GB| 29.83 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
|
| 80 |
+
| llama-65b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 34.55 GB| 37.05 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
|
| 81 |
+
| llama-65b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 31.40 GB| 33.90 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
|
| 82 |
+
| llama-65b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 28.06 GB| 30.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
|
| 83 |
+
| llama-65b.ggmlv3.q4_0.bin | q4_0 | 4 | 36.73 GB| 39.23 GB | Original quant method, 4-bit. |
|
| 84 |
+
| llama-65b.ggmlv3.q4_1.bin | q4_1 | 4 | 40.81 GB| 43.31 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
|
| 85 |
+
| llama-65b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 39.28 GB| 41.78 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
|
| 86 |
+
| llama-65b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 36.73 GB| 39.23 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
|
| 87 |
+
| llama-65b.ggmlv3.q5_0.bin | q5_0 | 5 | 44.89 GB| 47.39 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
|
| 88 |
+
| llama-65b.ggmlv3.q5_1.bin | q5_1 | 5 | 48.97 GB| 51.47 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
|
| 89 |
+
| llama-65b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 46.20 GB| 48.70 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
|
| 90 |
+
| llama-65b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 44.89 GB| 47.39 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
|
| 91 |
|
| 92 |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
|
| 93 |
|