File size: 2,139 Bytes
c9d05bc 7f5be19 c9d05bc 564ad6d c9d05bc |
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 |
---
model-index:
- name: abacaj/mistral-7b-sft
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 54.27
verified: false
- task:
type: text-generation
dataset:
type: mbpp
name: MBPP
metrics:
- name: pass@1
type: pass@1
value: 38.00
verified: false
- task:
type: text-generation
dataset:
type: mmlu
name: MMLU
metrics:
- name: pass@1
type: pass@1
value: 45.89
verified: false
language:
- en
---
How to run inference:
```python
import transformers
import torch
def fmt_prompt(prompt: str) -> str:
return f"""[Instructions]:\n{prompt}\n\n[Response]:"""
if __name__ == "__main__":
model_name = "abacaj/mistral-7b-sft"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
model = (
transformers.AutoModelForCausalLM.from_pretrained(
model_name,
)
.to("cuda:0")
.eval()
)
prompt = "If A is greater than B and B is greater than C does that make A greater than C?"
prompt_input = fmt_prompt(prompt)
inputs = tokenizer(prompt_input, return_tensors="pt").to(model.device)
input_ids_cutoff = inputs.input_ids.size(dim=1)
with torch.no_grad():
generated_ids = model.generate(
**inputs,
use_cache=True,
max_new_tokens=512,
temperature=0.2,
top_p=0.95,
do_sample=True,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
)
completion = tokenizer.decode(
generated_ids[0][input_ids_cutoff:],
skip_special_tokens=True,
)
print(completion)
```
Evals:
Code to train model:
https://github.com/abacaj/train-with-fsdp |