File size: 3,386 Bytes
fe1ad0f c1ec7d4 7455897 c1ec7d4 cd1a001 fe1ad0f c1ec7d4 7c4cfa7 c1ec7d4 7c4cfa7 fe1ad0f d4fef3a 7c4cfa7 d4fef3a 9d965a7 d4fef3a c1ec7d4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
---
tags:
- autotrain
- conversational
- meta-llama
- meta-llama/Llama-2-7b-hf
inference: false
widget:
- text: >
instruction: "If you are a doctor, please answer the medical questions based
on the patient's description."
input: "Hi, I had a subarachnoid bleed and coiling of brain aneurysm last
year. I am having some major bilateral temple pain along with numbness that
comes and goes in my left arm/hand/fingers. I have had headaches since the
aneurysm, but this is different. Also, my moods have been horrible for the
past few weeks."
response: ''
library_name: peft
---
```python
!huggingface-cli login
_| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|
_| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|
_|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|
_| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|
_| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|
To login, `huggingface_hub` requires a token generated from https://huggingface.co./settings/tokens .
Token: <your-hf-access-token>
```
```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer
import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
config = PeftConfig.from_pretrained("Ashishkr/llama2_medical_consultation")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf")
model = PeftModel.from_pretrained(model, "Ashishkr/llama2_medical_consultation").to(device)
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-hf")
```
```python
def llama_generate(
model: AutoModelForCausalLM,
tokenizer: AutoTokenizer,
prompt: str,
max_new_tokens: int = 128,
temperature: float = 0.92):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
inputs = tokenizer(
[prompt],
return_tensors="pt",
return_token_type_ids=False,
).to(
device
)
with torch.autocast("cuda", dtype=torch.bfloat16):
response = model.generate(
**inputs,
max_new_tokens=max_new_tokens,
temperature=temperature,
return_dict_in_generate=True,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
)
decoded_output = tokenizer.decode(
response["sequences"][0],
skip_special_tokens=True,
)
return decoded_output[len(prompt) :]
prompt = """
instruction: "If you are a doctor, please answer the medical questions based on the patient's description." \n
input: "Hi, I had a subarachnoid bleed and coiling of brain aneurysm last year.
I am having some major bilateral temple pain along with numbness that comes and
goes in my left arm/hand/fingers. I have had headaches since the aneurysm,
but this is different. Also, my moods have been horrible for the past few weeks.\n
response: """
response = llama_generate(
model,
tokenizer,
prompt,
max_new_tokens=100,
temperature=0.92,
)
print(response)
``` |