Downloads · 30 days
33
4% of all-time downloads
RichardErkhov/Morfoz-Aigap_-_Morfoz-LLM-8b-v1.0-gguf
Morfoz-Aigap_-_Morfoz-LLM-8b-v1.0-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
33
4% of all-time downloads
All-time downloads
791
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Morfoz-LLM-8b-v1.0 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Morfoz-LLM-8b-v1.0.Q2_K.gguf | Q2_K | 2.96GB |
| Morfoz-LLM-8b-v1.0.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| Morfoz-LLM-8b-v1.0.IQ3_S.gguf | IQ3_S | 3.43GB |
| Morfoz-LLM-8b-v1.0.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| Morfoz-LLM-8b-v1.0.IQ3_M.gguf | IQ3_M | 3.52GB |
| Morfoz-LLM-8b-v1.0.Q3_K.gguf | Q3_K | 3.74GB |
| Morfoz-LLM-8b-v1.0.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| Morfoz-LLM-8b-v1.0.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| Morfoz-LLM-8b-v1.0.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| Morfoz-LLM-8b-v1.0.Q4_0.gguf | Q4_0 | 4.34GB |
| Morfoz-LLM-8b-v1.0.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| Morfoz-LLM-8b-v1.0.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| Morfoz-LLM-8b-v1.0.Q4_K.gguf | Q4_K | 4.58GB |
| Morfoz-LLM-8b-v1.0.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| Morfoz-LLM-8b-v1.0.Q4_1.gguf | Q4_1 | 4.78GB |
| Morfoz-LLM-8b-v1.0.Q5_0.gguf | Q5_0 | 5.21GB |
| Morfoz-LLM-8b-v1.0.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| Morfoz-LLM-8b-v1.0.Q5_K.gguf | Q5_K | 5.34GB |
| Morfoz-LLM-8b-v1.0.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| Morfoz-LLM-8b-v1.0.Q5_1.gguf | Q5_1 | 5.65GB |
| Morfoz-LLM-8b-v1.0.Q6_K.gguf | Q6_K | 6.14GB |
| Morfoz-LLM-8b-v1.0.Q8_0.gguf | Q8_0 | 7.95GB |
license: apache-2.0 language:
This model is an extended version of a Llama-3 8B Instruct-based Large Language Model (LLM) for Turkish. It was trained on a cleaned Turkish raw dataset. We utilized Turkish instruction sets created from various open-source for fine-tuning with the LORA method.
lora_alpha: 16lora_dropout: 0.05r: 64target_modules: "all-linear"
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
tokenizer = AutoTokenizer.from_pretrained("Morfoz-Aigap/Morfoz-LLM-8b-v1.0")
model = AutoModelForCausalLM.from_pretrained("Morfoz-Aigap/Morfoz-LLM-8b-v1.0", torch_dtype=torch.bfloat16, device_map={"": 0},low_cpu_mem_usage=True)
messages = [
{"role": "user", "content": "Kırmızı başlıklı kız adında kısa bir çocuk hikayesi yazabilir misin?"}
]
top_k = 50
top_p = 0.9
temperature = 0.6
def get_formatted_input(messages):
for item in messages:
if item['role'] == "user":
item['content'] = item['content']
break
conversation = '\n\n'.join(["User: " + item["content"] if item["role"] == "user" else "Assistant: " + item["content"] for item in messages]) + "\n\nAssistant:"
formatted_input = "\n\n" + conversation
return formatted_input
formatted_input = get_formatted_input(messages)
print(formatted_input)
tokenized_prompt = tokenizer(tokenizer.bos_token + formatted_input, return_tensors="pt").to(model.device)
terminators = [
tokenizer.eos_token_id,
tokenizer.convert_tokens_to_ids("<|eot_id|>")
]
outputs = model.generate(input_ids=tokenized_prompt.input_ids, do_sample = True, attention_mask=tokenized_prompt.attention_mask, max_new_tokens=256, eos_token_id=terminators, top_p=top_p, temperature=temperature)
response = outputs[0][tokenized_prompt.input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))