Update README.md
Browse files
README.md
CHANGED
@@ -44,19 +44,23 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardMath-13B-V1.0-GGML)
|
45 |
* [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardMath-13B-V1.0)
|
46 |
|
47 |
-
## Prompt template:
|
|
|
|
|
|
|
|
|
48 |
|
49 |
```
|
50 |
-
Below is an instruction that describes a task. Write a response that appropriately completes the request
|
|
|
51 |
|
52 |
|
53 |
-
|
54 |
-
{prompt}
|
55 |
|
56 |
|
57 |
-
### Response: Let's think step by step.
|
58 |
```
|
59 |
-
|
|
|
60 |
<!-- compatibility_ggml start -->
|
61 |
## Compatibility
|
62 |
|
|
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardMath-13B-V1.0-GGML)
|
45 |
* [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardMath-13B-V1.0)
|
46 |
|
47 |
+
## Prompt template:
|
48 |
+
|
49 |
+
❗<b>Note for model system prompts usage:</b>
|
50 |
+
|
51 |
+
**Default version:**
|
52 |
|
53 |
```
|
54 |
+
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
|
55 |
+
```
|
56 |
|
57 |
|
58 |
+
**CoT Version:** (❗For the **simple** math questions, we do NOT recommend to use the CoT prompt.)
|
|
|
59 |
|
60 |
|
|
|
61 |
```
|
62 |
+
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: Let's think step by step."
|
63 |
+
```
|
64 |
<!-- compatibility_ggml start -->
|
65 |
## Compatibility
|
66 |
|