Initial GPTQ model commit
Browse files
README.md
CHANGED
@@ -44,10 +44,10 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
|
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML)
|
45 |
* [Open-Orca's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B)
|
46 |
|
47 |
-
## Prompt template:
|
48 |
|
49 |
```
|
50 |
-
|
51 |
```
|
52 |
|
53 |
## Provided files
|
@@ -141,7 +141,7 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
|
|
141 |
"""
|
142 |
|
143 |
prompt = "Tell me about AI"
|
144 |
-
prompt_template=f'''
|
145 |
'''
|
146 |
|
147 |
print("\n\n*** Generate:")
|
|
|
44 |
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML)
|
45 |
* [Open-Orca's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B)
|
46 |
|
47 |
+
## Prompt template: OpenChat Llama2 V1
|
48 |
|
49 |
```
|
50 |
+
User: {prompt}<|end_of_turn|>Assistant:
|
51 |
```
|
52 |
|
53 |
## Provided files
|
|
|
141 |
"""
|
142 |
|
143 |
prompt = "Tell me about AI"
|
144 |
+
prompt_template=f'''User: {prompt}<|end_of_turn|>Assistant:
|
145 |
'''
|
146 |
|
147 |
print("\n\n*** Generate:")
|