YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
phi-3-tiny-random - GGUF
- Model creator: https://huggingface.co/yujiepan/
- Original model: https://huggingface.co/yujiepan/phi-3-tiny-random/
Name | Quant method | Size |
---|---|---|
phi-3-tiny-random.Q2_K.gguf | Q2_K | 0.0GB |
phi-3-tiny-random.IQ3_XS.gguf | IQ3_XS | 0.0GB |
phi-3-tiny-random.IQ3_S.gguf | IQ3_S | 0.0GB |
phi-3-tiny-random.Q3_K_S.gguf | Q3_K_S | 0.0GB |
phi-3-tiny-random.IQ3_M.gguf | IQ3_M | 0.0GB |
phi-3-tiny-random.Q3_K.gguf | Q3_K | 0.0GB |
phi-3-tiny-random.Q3_K_M.gguf | Q3_K_M | 0.0GB |
phi-3-tiny-random.Q3_K_L.gguf | Q3_K_L | 0.0GB |
phi-3-tiny-random.IQ4_XS.gguf | IQ4_XS | 0.0GB |
phi-3-tiny-random.Q4_0.gguf | Q4_0 | 0.0GB |
phi-3-tiny-random.IQ4_NL.gguf | IQ4_NL | 0.0GB |
phi-3-tiny-random.Q4_K_S.gguf | Q4_K_S | 0.0GB |
phi-3-tiny-random.Q4_K.gguf | Q4_K | 0.0GB |
phi-3-tiny-random.Q4_K_M.gguf | Q4_K_M | 0.0GB |
phi-3-tiny-random.Q4_1.gguf | Q4_1 | 0.0GB |
phi-3-tiny-random.Q5_0.gguf | Q5_0 | 0.0GB |
phi-3-tiny-random.Q5_K_S.gguf | Q5_K_S | 0.0GB |
phi-3-tiny-random.Q5_K.gguf | Q5_K | 0.0GB |
phi-3-tiny-random.Q5_K_M.gguf | Q5_K_M | 0.0GB |
phi-3-tiny-random.Q5_1.gguf | Q5_1 | 0.0GB |
phi-3-tiny-random.Q6_K.gguf | Q6_K | 0.0GB |
phi-3-tiny-random.Q8_0.gguf | Q8_0 | 0.0GB |
Original model description:
library_name: transformers pipeline_tag: text-generation inference: true widget: - text: Hello! example_title: Hello world group: Python
This model is randomly initialized, using the config from microsoft/Phi-3-mini-128k-instruct but with smaller size. Note the model is in float16.
Codes:
import transformers
import torch
import os
from huggingface_hub import create_repo, upload_folder
source_model_id = 'microsoft/Phi-3-mini-128k-instruct'
save_path = '/tmp/yujiepan/phi-3-tiny-random'
repo_id = 'yujiepan/phi-3-tiny-random'
config = transformers.AutoConfig.from_pretrained(
source_model_id, trust_remote_code=True)
config.hidden_size = 16
config.intermediate_size = 32
config.num_attention_heads = 4
config.num_hidden_layers = 2
config.num_key_value_heads = 4
config.rope_scaling['long_factor'] = [1.0299, 1.0499]
config.rope_scaling['short_factor'] = [1.05, 1.05]
model = transformers.AutoModelForCausalLM.from_config(
config, trust_remote_code=True)
model = model.to(torch.float16)
model.save_pretrained(save_path)
tokenizer = transformers.AutoTokenizer.from_pretrained(
source_model_id, trust_remote_code=True)
tokenizer.save_pretrained(save_path)
result = transformers.pipelines.pipeline(
'text-generation',
model=model.float(), tokenizer=tokenizer)('Hello')
print(result)
os.system(f'ls -alh {save_path}')
create_repo(repo_id, exist_ok=True)
upload_folder(repo_id=repo_id, folder_path=save_path)
from transformers import AutoProcessor
AutoProcessor.from_pretrained(source_model_id, trust_remote_code=True).push_to_hub(repo_id)
- Downloads last month
- 20