Update README.md
#1
by
WizardLM
- opened
README.md
CHANGED
@@ -38,17 +38,22 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
|
|
38 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardMath-7B-V1.0-GGML)
|
39 |
* [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardMath-7b-V1.0)
|
40 |
|
41 |
-
## Prompt template:
|
|
|
|
|
|
|
|
|
42 |
|
43 |
```
|
44 |
-
Below is an instruction that describes a task. Write a response that appropriately completes the request
|
|
|
45 |
|
46 |
|
47 |
-
|
48 |
-
{prompt}
|
49 |
|
50 |
|
51 |
-
|
|
|
52 |
```
|
53 |
|
54 |
## Provided files and GPTQ parameters
|
|
|
38 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardMath-7B-V1.0-GGML)
|
39 |
* [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardMath-7b-V1.0)
|
40 |
|
41 |
+
## Prompt template:
|
42 |
+
|
43 |
+
❗<b>Note for model system prompts usage:</b>
|
44 |
+
|
45 |
+
**Default version:**
|
46 |
|
47 |
```
|
48 |
+
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
|
49 |
+
```
|
50 |
|
51 |
|
52 |
+
**CoT Version:** (❗For the **simple** math questions, we do NOT recommend to use the CoT prompt.)
|
|
|
53 |
|
54 |
|
55 |
+
```
|
56 |
+
"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."
|
57 |
```
|
58 |
|
59 |
## Provided files and GPTQ parameters
|