Update README.md
Browse files
README.md
CHANGED
@@ -95,7 +95,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
|
|
95 |
--speculator_path=ibm-fms/codellama-13b-accelerator \
|
96 |
--speculator_source=hf \
|
97 |
--top_k_tokens_per_head=4,3,2,2,2,2,2 \
|
98 |
-
--prompt_type=code
|
99 |
--compile \
|
100 |
--compile_mode=reduce-overhead
|
101 |
```
|
@@ -111,7 +111,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
|
|
111 |
--speculator_path=ibm-fms/codellama-13b-accelerator \
|
112 |
--speculator_source=hf \
|
113 |
--top_k_tokens_per_head=4,3,2,2,2,2,2 \
|
114 |
-
--prompt_type=code
|
115 |
--compile \
|
116 |
```
|
117 |
|
@@ -127,7 +127,7 @@ python fms-extras/scripts/paged_speculative_inference.py \
|
|
127 |
--speculator_source=hf \
|
128 |
--batch_input \
|
129 |
--top_k_tokens_per_head=4,3,2,2,2,2,2 \
|
130 |
-
--prompt_type=code
|
131 |
--compile \
|
132 |
```
|
133 |
|
|
|
95 |
--speculator_path=ibm-fms/codellama-13b-accelerator \
|
96 |
--speculator_source=hf \
|
97 |
--top_k_tokens_per_head=4,3,2,2,2,2,2 \
|
98 |
+
--prompt_type=code \
|
99 |
--compile \
|
100 |
--compile_mode=reduce-overhead
|
101 |
```
|
|
|
111 |
--speculator_path=ibm-fms/codellama-13b-accelerator \
|
112 |
--speculator_source=hf \
|
113 |
--top_k_tokens_per_head=4,3,2,2,2,2,2 \
|
114 |
+
--prompt_type=code \
|
115 |
--compile \
|
116 |
```
|
117 |
|
|
|
127 |
--speculator_source=hf \
|
128 |
--batch_input \
|
129 |
--top_k_tokens_per_head=4,3,2,2,2,2,2 \
|
130 |
+
--prompt_type=code \
|
131 |
--compile \
|
132 |
```
|
133 |
|