Update transformers_inference_example.py
Browse files
transformers_inference_example.py
CHANGED
|
@@ -8,7 +8,7 @@ import bitsandbytes, flash_attn
|
|
| 8 |
|
| 9 |
tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', trust_remote_code=True)
|
| 10 |
model = MixtralForCausalLM.from_pretrained(
|
| 11 |
-
"
|
| 12 |
torch_dtype=torch.float16,
|
| 13 |
device_map="auto",
|
| 14 |
load_in_8bit=False,
|
|
|
|
| 8 |
|
| 9 |
tokenizer = LlamaTokenizer.from_pretrained('NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO', trust_remote_code=True)
|
| 10 |
model = MixtralForCausalLM.from_pretrained(
|
| 11 |
+
"vicky4s4s/Mistral-instruct-46B",
|
| 12 |
torch_dtype=torch.float16,
|
| 13 |
device_map="auto",
|
| 14 |
load_in_8bit=False,
|