Xin Liu
commited on
Commit
•
5ac23c1
1
Parent(s):
fecbb67
Update
Browse filesSigned-off-by: Xin Liu <[email protected]>
README.md
CHANGED
|
@@ -57,9 +57,29 @@ tags:
|
|
| 57 |
- Run as LlamaEdge service
|
| 58 |
|
| 59 |
```bash
|
| 60 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-mini-4k-instruct-
|
| 61 |
llama-api-server.wasm \
|
| 62 |
--prompt-template phi-3-chat \
|
| 63 |
--ctx-size 3072 \
|
| 64 |
--model-name phi-3-mini
|
| 65 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
- Run as LlamaEdge service
|
| 58 |
|
| 59 |
```bash
|
| 60 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-mini-4k-instruct-Q5_K_M.gguf \
|
| 61 |
llama-api-server.wasm \
|
| 62 |
--prompt-template phi-3-chat \
|
| 63 |
--ctx-size 3072 \
|
| 64 |
--model-name phi-3-mini
|
| 65 |
```
|
| 66 |
+
|
| 67 |
+
## Quantized GGUF Models
|
| 68 |
+
|
| 69 |
+
| Name | Quant method | Bits | Size | Use case |
|
| 70 |
+
| ---- | ---- | ---- | ---- | ----- |
|
| 71 |
+
| [Phi-3-mini-4k-instruct-Q2_K.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q2_K.gguf) | Q2_K | 2 | 1.42 GB| smallest, significant quality loss - not recommended for most purposes |
|
| 72 |
+
| [Phi-3-mini-4k-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 2.09 GB| small, substantial quality loss |
|
| 73 |
+
| [Phi-3-mini-4k-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 1.96 GB| very small, high quality loss |
|
| 74 |
+
| [Phi-3-mini-4k-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 1.68 GB| very small, high quality loss |
|
| 75 |
+
| [Phi-3-mini-4k-instruct-Q4_0.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q4_0.gguf) | Q4_0 | 4 | 2.18 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 76 |
+
| [Phi-3-mini-4k-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.39 GB| medium, balanced quality - recommended |
|
| 77 |
+
| [Phi-3-mini-4k-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 2.19 GB| small, greater quality loss |
|
| 78 |
+
| [Phi-3-mini-4k-instruct-Q5_0.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q5_0.gguf) | Q5_0 | 5 | 2.64 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 79 |
+
| [Phi-3-mini-4k-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 2.82 GB| large, very low quality loss - recommended |
|
| 80 |
+
| [Phi-3-mini-4k-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 2.64 GB| large, low quality loss - recommended |
|
| 81 |
+
| [Phi-3-mini-4k-instruct-Q6_K.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q6_K.gguf) | Q6_K | 6 | 3.14 GB| very large, extremely low quality loss |
|
| 82 |
+
| [Phi-3-mini-4k-instruct-Q8_0.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-Q8_0.gguf) | Q8_0 | 8 | 4.06 GB| very large, extremely low quality loss - not recommended |
|
| 83 |
+
| [Phi-3-mini-4k-instruct-f16.gguf](https://huggingface.co/second-state/Phi-3-mini-4k-instruct-GGUF/blob/main/Phi-3-mini-4k-instruct-f16.gguf) | f16 | 16 | 7.64 GB| |
|
| 84 |
+
|
| 85 |
+
*Quantized with llama.cpp b2717.*
|