Commit
•
3febd68
1
Parent(s):
a822ede
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -23,9 +23,7 @@ quantized_by: Second State Inc.
|
|
| 23 |
|
| 24 |
## Run with LlamaEdge
|
| 25 |
|
| 26 |
-
- LlamaEdge version:
|
| 27 |
-
|
| 28 |
-
<!-- - LlamaEdge version: [v0.11.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.11.2)
|
| 29 |
|
| 30 |
- Prompt template
|
| 31 |
|
|
@@ -35,11 +33,11 @@ quantized_by: Second State Inc.
|
|
| 35 |
|
| 36 |
```text
|
| 37 |
<s>[INST] {user_message_1} [/INST]{assistant_message_1}</s>[INST] {user_message_2} [/INST]{assistant_message_2}</s>
|
| 38 |
-
```
|
| 39 |
|
| 40 |
- Context size: `32000`
|
| 41 |
|
| 42 |
-
|
| 43 |
|
| 44 |
```bash
|
| 45 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:mathstral-7B-v0.1-Q5_K_M.gguf \
|
|
@@ -56,7 +54,7 @@ quantized_by: Second State Inc.
|
|
| 56 |
llama-chat.wasm \
|
| 57 |
--prompt-template mistral-instruct \
|
| 58 |
--ctx-size 32000
|
| 59 |
-
```
|
| 60 |
|
| 61 |
## Quantized GGUF Models
|
| 62 |
|
|
|
|
| 23 |
|
| 24 |
## Run with LlamaEdge
|
| 25 |
|
| 26 |
+
- LlamaEdge version: [v0.12.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.3)
|
|
|
|
|
|
|
| 27 |
|
| 28 |
- Prompt template
|
| 29 |
|
|
|
|
| 33 |
|
| 34 |
```text
|
| 35 |
<s>[INST] {user_message_1} [/INST]{assistant_message_1}</s>[INST] {user_message_2} [/INST]{assistant_message_2}</s>
|
| 36 |
+
```
|
| 37 |
|
| 38 |
- Context size: `32000`
|
| 39 |
|
| 40 |
+
- Run as LlamaEdge service
|
| 41 |
|
| 42 |
```bash
|
| 43 |
wasmedge --dir .:. --nn-preload default:GGML:AUTO:mathstral-7B-v0.1-Q5_K_M.gguf \
|
|
|
|
| 54 |
llama-chat.wasm \
|
| 55 |
--prompt-template mistral-instruct \
|
| 56 |
--ctx-size 32000
|
| 57 |
+
```
|
| 58 |
|
| 59 |
## Quantized GGUF Models
|
| 60 |
|