You can deploy this model and start earning money today!

RichardErkhov/
yujiepan_-_llama-3.2-tiny-random-gguf

Name: yujiepan_-_llama-3.2-tiny-random-gguf
Availability: InStock

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3.2-tiny-random - GGUF

Model creator: https://huggingface.co/yujiepan/
Original model: https://huggingface.co/yujiepan/llama-3.2-tiny-random/

Name	Quant method	Size
llama-3.2-tiny-random.Q2_K.gguf	Q2_K	0.01GB
llama-3.2-tiny-random.IQ3_XS.gguf	IQ3_XS	0.01GB
llama-3.2-tiny-random.IQ3_S.gguf	IQ3_S	0.01GB
llama-3.2-tiny-random.Q3_K_S.gguf	Q3_K_S	0.01GB
llama-3.2-tiny-random.IQ3_M.gguf	IQ3_M	0.01GB
llama-3.2-tiny-random.Q3_K.gguf	Q3_K	0.01GB
llama-3.2-tiny-random.Q3_K_M.gguf	Q3_K_M	0.01GB
llama-3.2-tiny-random.Q3_K_L.gguf	Q3_K_L	0.01GB
llama-3.2-tiny-random.IQ4_XS.gguf	IQ4_XS	0.01GB
llama-3.2-tiny-random.Q4_0.gguf	Q4_0	0.01GB
llama-3.2-tiny-random.IQ4_NL.gguf	IQ4_NL	0.01GB
llama-3.2-tiny-random.Q4_K_S.gguf	Q4_K_S	0.01GB
llama-3.2-tiny-random.Q4_K.gguf	Q4_K	0.01GB
llama-3.2-tiny-random.Q4_K_M.gguf	Q4_K_M	0.01GB
llama-3.2-tiny-random.Q4_1.gguf	Q4_1	0.01GB
llama-3.2-tiny-random.Q5_0.gguf	Q5_0	0.01GB
llama-3.2-tiny-random.Q5_K_S.gguf	Q5_K_S	0.01GB
llama-3.2-tiny-random.Q5_K.gguf	Q5_K	0.01GB
llama-3.2-tiny-random.Q5_K_M.gguf	Q5_K_M	0.01GB
llama-3.2-tiny-random.Q5_1.gguf	Q5_1	0.01GB
llama-3.2-tiny-random.Q6_K.gguf	Q6_K	0.01GB
llama-3.2-tiny-random.Q8_0.gguf	Q8_0	0.01GB

Original model description:

library_name: transformers pipeline_tag: text-generation inference: true widget:

text: Hello! example_title: Hello world group: Python

This model is for debugging. It is randomly initialized using the config from meta-llama/Llama-3.2-3B-Instruct but with smaller size.

Codes:

python

import os

import torch
import transformers
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, GenerationConfig, pipeline, set_seed

model_id = "meta-llama/Llama-3.2-3B-Instruct"
repo_id = "yujiepan/llama-3.2-tiny-random"
save_path = f"/tmp/{repo_id}"

config = AutoConfig.from_pretrained(model_id, trust_remote_code=True)
config._name_or_path = model_id
config.hidden_size = 8
config.intermediate_size = 16
config.num_attention_heads = 2
config.num_key_value_heads = 1
config.head_dim = 4
config.num_hidden_layers = 2
config.torch_dtype = "bfloat16"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
tokenizer.save_pretrained(save_path)

model = AutoModelForCausalLM.from_config(
    config, torch_dtype=torch.bfloat16, attn_implementation="sdpa", trust_remote_code=True
)
model.generation_config = GenerationConfig.from_pretrained(
    model_id, trust_remote_code=True)

set_seed(42)
with torch.no_grad():
    for _, p in sorted(model.named_parameters()):
        torch.nn.init.uniform_(p, -0.2, 0.2)

model.save_pretrained(save_path)

pipe = pipeline("text-generation", model=save_path, device="cpu",
                trust_remote_code=True, max_new_tokens=20)
print(pipe("Hello World!"))

RichardErkhov/yujiepan_-_llama-3.2-tiny-random-gguf

Original model description:

RichardErkhov/
yujiepan_-_llama-3.2-tiny-random-gguf