Update config.json

1 - # alpaca_prompt = Copied from above
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
inputs = tokenizer(
[
alpaca_prompt.format(
# "Continue the fibonnaci sequence.", # instruction
# "1, 1, 2, 3, 5, 8", # input
"", # output - leave this blank for generation!
)
], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 128, use_cache = True)
tokenizer.batch_decode(outputs)

['Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Input:\nContinue the fibonnaci sequence.\n\n### Output:\n1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233, 377, 610, 987, 1597, 2584, 4181, 6765, 10946, 17711, 28657, 46368, 75025, 121393, 196728, 318101']

2 - # alpaca_prompt = Copied from above
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
inputs = tokenizer(
[
alpaca_prompt.format(
# "What is fibonacci sequence?", # instruction
"", # input
"", # output - leave this blank for generation!
)
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 256)

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Input:
What is fibonacci sequence?

### Output:
The Fibonacci sequence is a series of numbers in which each number is the sum of the two preceding ones, usually starting with 0 and 1. The sequence goes like this: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89, 144, 233, 377, 610, 987, 1597, 2584, 4181, 6765, 10946, 17711, 28657, 46368, 75025, 121393, 196728, 328101, 544829, 973530, 1518361, 2492891, 4011452, 6504307, 9518768, 15023075

3 - if False:
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "lora_model", # YOUR MODEL YOU USED FOR TRAINING
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference

# alpaca_prompt = You MUST copy from above!

inputs = tokenizer(
[
alpaca_prompt.format(
# "Crie uma IA. Ela será treinada para conversar por chat e escrever códigos em python conforme solicitada, após ser treinada para essas tarefas.", # instruction
"", # input
"", # output - leave this blank for generation!
)
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 4096)

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Input:
Crie uma IA. Ela será treinada para conversar por chat e escrever codigos em python conforme solicitada, após ser treinada para essas tarefas.

### Output:
Here is a simple Python program that uses the OpenAI's ChatGPT API to simulate a chatbot:

```python
import openai
from openai import ChatGPT

# Initialize the ChatGPT API
openai.api_key = "YOUR_API_KEY"

# Create a ChatGPT model
model = ChatGPT(model_name="gpt-3.5-turbo")

# Create a prompt
prompt = "Write a python program that takes a number as input and prints out the square of that number."

# Send the prompt to the ChatGPT model
response = model.create(input=prompt)

# Print the response
print(response)
```

This program will output a Python program that takes a number as input and prints out the square of that number.<|endoftext|>

config.json

@@ -1,3 +1,31 @@
 {
-    "model_type": "qwen2"
+  "_name_or_path": "unsloth/qwen2-0.5b-bnb-4bit",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151646,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.3",
+  "unsloth_version": "2024.8",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }