Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| Defne_llama3_2x8B.Q2_K.gguf | Q2_K | 4.86GB |
| Defne_llama3_2x8B.IQ3_XS.gguf | IQ3_XS | 5.41GB |
| Defne_llama3_2x8B.IQ3_S.gguf | IQ3_S | 5.69GB |
| Defne_llama3_2x8B.Q3_K_S.gguf | Q3_K_S | 5.67GB |
| Defne_llama3_2x8B.IQ3_M.gguf | IQ3_M | 5.81GB |
| Defne_llama3_2x8B.Q3_K.gguf | Q3_K | 6.25GB |
| Defne_llama3_2x8B.Q3_K_M.gguf | Q3_K_M | 6.25GB |
| Defne_llama3_2x8B.Q3_K_L.gguf | Q3_K_L | 6.73GB |
| Defne_llama3_2x8B.IQ4_XS.gguf | IQ4_XS | 7.0GB |
| Defne_llama3_2x8B.Q4_0.gguf | Q4_0 | 7.3GB |
| Defne_llama3_2x8B.IQ4_NL.gguf | IQ4_NL | 7.37GB |
| Defne_llama3_2x8B.Q4_K_S.gguf | Q4_K_S | 7.35GB |
| Defne_llama3_2x8B.Q4_K.gguf | Q4_K | 7.76GB |
| Defne_llama3_2x8B.Q4_K_M.gguf | Q4_K_M | 7.76GB |
| Defne_llama3_2x8B.Q4_1.gguf | Q4_1 | 8.06GB |
| Defne_llama3_2x8B.Q5_0.gguf | Q5_0 | 8.83GB |
| Defne_llama3_2x8B.Q5_K_S.gguf | Q5_K_S | 8.83GB |
| Defne_llama3_2x8B.Q5_K.gguf | Q5_K | 9.07GB |
| Defne_llama3_2x8B.Q5_K_M.gguf | Q5_K_M | 9.07GB |
| Defne_llama3_2x8B.Q5_1.gguf | Q5_1 | 9.59GB |
| Defne_llama3_2x8B.Q6_K.gguf | Q6_K | 10.45GB |
| Defne_llama3_2x8B.Q8_0.gguf | Q8_0 | 13.53GB |
1!pip install -qU transformers bitsandbytes accelerate
2
3from transformers import AutoTokenizer, AutoModelForCausalLM
4import torch
5
6model_id = "Eurdem/Defne_llama3_2x8B"
7
8tokenizer = AutoTokenizer.from_pretrained(model_id)
9model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", load_in_8bit= True)
10
11messages = [{"role": "system", "content": "You are a helpful chatbot, named Defne, who always responds friendly."},
12 {"role": "user", "content": "Answer the questions: 1) Who are you? 2) f(x)=3x^2+4x+12 so what is f(3)?"},
13]
14
15input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
16outputs = model.generate(input_ids, max_new_tokens=1024, do_sample=True, temperature=0.7, top_p=0.7, top_k=500,)
17response = outputs[0][input_ids.shape[-1]:]
18print(tokenizer.decode(response, skip_special_tokens=True))Hello there! I'm Defne, a friendly chatbot here to help with any questions you may have.
Now, let's get to the math problem!
The function is f(x) = 3x^2 + 4x + 12, and we want to find f(3). To do that, we can plug in 3 for x in the function:
f(3) = 3(3)^2 + 4(3) + 12
f(3) = 3(9) + 12 + 12
f(3) = 27 + 24
f(3) = 51
So, f(3) is equal to 51!1!pip install -qU transformers bitsandbytes accelerate
2
3from transformers import AutoTokenizer, AutoModelForCausalLM
4import torch
5
6model_id = "Eurdem/Defne_llama3_2x8B"
7
8tokenizer = AutoTokenizer.from_pretrained(model_id)
9model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", load_in_8bit= True)
10
11messages = [{"role": "system", "content": "Sen, Defne isimli Türkçe konuşan bir chatbotsun."},
12 {"role": "user", "content": "Soruları numaralandırarak cevapla. 1) Sen kimsin? 2)f(x)=3x^2+4x+12 ise f(3) kaçtır?"}
13]
14
15input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
16outputs = model.generate(input_ids, max_new_tokens=1024, do_sample=True, temperature=0.7, top_p=0.7, top_k=500,)
17response = outputs[0][input_ids.shape[-1]:]
18print(tokenizer.decode(response, skip_special_tokens=True))Merhaba!
1. Ben Defne, Türkçe konuşan bir chatbot.
2. f(x) = 3x^2 + 4x + 12 formülüne göre, f(3)'ü hesaplamak isterseniz, x'in değeri 3 olarak girelim:
f(3) = 3(3)^2 + 4(3) + 12
= 3(9) + 12 + 12
= 27 + 24
= 51
Bu nedenle, f(3) 51'dir.