File size: 2,171 Bytes
dfd565c 955dece e675cff dfd565c 955dece ff90418 955dece bd31562 1d23e84 955dece b171526 bc51176 1d23e84 1bda8ad b171526 1d23e84 b171526 782ecb2 b171526 1bda8ad 955dece |
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 |
---
license: apache-2.0
pipeline_tag: text-generation
tags:
- finetuned
inference:
parameters:
temperature: 0.01
---
A Mistral7B Instruct (https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
Finetune using QLoRA on the docs available in https://docs.modular.com/mojo/
The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) generative text model using a variety of publicly available conversation datasets.
## Instruction format
```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
import torch
device = "cuda" # the device to load the model onto
model_name = "mcysqrd/MODULARMOJO_Mistral_V1"
model = AutoModelForCausalLM.from_pretrained(model_name,
use_flash_attention_2=True,
max_memory={0: "24GB"},
device_map="auto",
trust_remote_code=True,
low_cpu_mem_usage=True,
return_dict=True,
torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained(model_name,add_bos_token=True,trust_remote_code=True)
model.config.use_cache = True
def stream(user_prompt):
runtimeFlag = "cuda:0"
system_prompt = 'MODULAR_MOJO'
B_INST, E_INST = "[INST]", "[/INST]"
prompt = f"{system_prompt}{B_INST}{user_prompt.strip()}\n{E_INST}"
inputs = tokenizer([prompt], return_tensors="pt").to(runtimeFlag)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=1600)
stream("""can you translate this python code to mojo to make more performant making T as struct?
class T():
self.init(v:float):
self.value=v
def sum_objects(a:T,b:T)->T:
return T(a.v+b.v)""")
``` |