Downloads · 30 days
65
4% of all-time downloads
RichardErkhov/lazarohurtado_-_Qwen1.5-0.5B-OpenIT-gguf
lazarohurtado_-_Qwen1.5-0.5B-OpenIT-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
65
4% of all-time downloads
All-time downloads
1.5K
Public
Repo size
7.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf8.9 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Qwen1.5-0.5B-OpenIT - GGUF
| Name | Quant method | Size |
|---|---|---|
| Qwen1.5-0.5B-OpenIT.Q2_K.gguf | Q2_K | 0.28GB |
| Qwen1.5-0.5B-OpenIT.IQ3_XS.gguf | IQ3_XS | 0.3GB |
| Qwen1.5-0.5B-OpenIT.IQ3_S.gguf | IQ3_S | 0.31GB |
| Qwen1.5-0.5B-OpenIT.Q3_K_S.gguf | Q3_K_S | 0.31GB |
| Qwen1.5-0.5B-OpenIT.IQ3_M.gguf | IQ3_M | 0.32GB |
| Qwen1.5-0.5B-OpenIT.Q3_K.gguf | Q3_K | 0.33GB |
| Qwen1.5-0.5B-OpenIT.Q3_K_M.gguf | Q3_K_M | 0.33GB |
| Qwen1.5-0.5B-OpenIT.Q3_K_L.gguf | Q3_K_L | 0.34GB |
| Qwen1.5-0.5B-OpenIT.IQ4_XS.gguf | IQ4_XS | 0.36GB |
| Qwen1.5-0.5B-OpenIT.Q4_0.gguf | Q4_0 | 0.33GB |
| Qwen1.5-0.5B-OpenIT.IQ4_NL.gguf | IQ4_NL | 0.37GB |
| Qwen1.5-0.5B-OpenIT.Q4_K_S.gguf | Q4_K_S | 0.37GB |
| Qwen1.5-0.5B-OpenIT.Q4_K.gguf | Q4_K | 0.38GB |
| Qwen1.5-0.5B-OpenIT.Q4_K_M.gguf | Q4_K_M | 0.38GB |
| Qwen1.5-0.5B-OpenIT.Q4_1.gguf | Q4_1 | 0.39GB |
| Qwen1.5-0.5B-OpenIT.Q5_0.gguf | Q5_0 | 0.42GB |
| Qwen1.5-0.5B-OpenIT.Q5_K_S.gguf | Q5_K_S | 0.42GB |
| Qwen1.5-0.5B-OpenIT.Q5_K.gguf | Q5_K | 0.43GB |
| Qwen1.5-0.5B-OpenIT.Q5_K_M.gguf | Q5_K_M | 0.43GB |
| Qwen1.5-0.5B-OpenIT.Q5_1.gguf | Q5_1 | 0.45GB |
| Qwen1.5-0.5B-OpenIT.Q6_K.gguf | Q6_K | 0.48GB |
| Qwen1.5-0.5B-OpenIT.Q8_0.gguf | Q8_0 | 0.62GB |
datasets:
Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"lazarohurtado/Qwen1.5-0.5B-OpenIT",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("lazarohurtado/Qwen1.5-0.5B-OpenIT")
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]