|
|
--- |
|
|
base_model: unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- trl |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
datasets: |
|
|
- GeneralReasoning/GeneralThought-430K |
|
|
- isaiahbjork/cot-logic-reasoning |
|
|
--- |
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** alibidaran |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-unsloth-bnb-4bit |
|
|
- **Finedtuned with SFT Algorithm** |
|
|
## Direct Usages: |
|
|
``` python |
|
|
from transformers import TextStreamer |
|
|
from unsloth import FastLanguageModel |
|
|
import torch |
|
|
max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally! |
|
|
dtype = 'Bfloat16' # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+ |
|
|
load_in_4bit = True |
|
|
model, tokenizer = FastLanguageModel.from_pretrained( |
|
|
model_name ="alibidaran/LLAMA3-instructive_reasoning", |
|
|
max_seq_length = max_seq_length, |
|
|
#dtype = dtype, |
|
|
load_in_4bit = load_in_4bit, |
|
|
#fast_inference = True, # Enable vLLM fast inference |
|
|
max_lora_rank = 128, |
|
|
gpu_memory_utilization = 0.6, # Reduce if out of memory |
|
|
# token = "hf_...", # use one if using gated models like meta-llama/Llama-2-7b-hf |
|
|
) |
|
|
FastLanguageModel.for_inference(model) # Enable native 2x faster inference |
|
|
system_prompt=""" |
|
|
You are a reasonable expert who thinks and answer the users question. |
|
|
Before respond first think and create a chain of thoughts in your mind. |
|
|
Then respond to the client. |
|
|
Your chain of thought and reflection must be in <thinking>..</thinking> format and your respond |
|
|
should be in the <output>..</output> format. |
|
|
""" |
|
|
|
|
|
messages = [ |
|
|
{'role':'system','content':system_prompt}, |
|
|
{"role": "user", "content":'How many r has the word of strawberry?' }, |
|
|
|
|
|
] |
|
|
inputs = tokenizer.apply_chat_template( |
|
|
messages, |
|
|
tokenize = True, |
|
|
add_generation_prompt = True, # Must add for generation |
|
|
return_tensors = "pt", |
|
|
).to("cuda") |
|
|
|
|
|
text_streamer = TextStreamer(tokenizer, skip_prompt = True) |
|
|
_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens =2048, |
|
|
use_cache = True, temperature = 0.7, min_p = 0.9) |
|
|
``` |
|
|
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
