falcon-mamba-tiny-random

60
—
by
yujiepan
Language Model
OTHER
New
60 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Training Data Analysis

🔴 Low Quality (2.5/10)

Researched training datasets used by falcon-mamba-tiny-random with quality assessment

Specialized For

general
science

Training Datasets (1)

common crawl
🔴 2.5/10
general
science
Key Strengths
  • •Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
  • •Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
  • •Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...
Considerations
  • •Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
  • •Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

create_repo(repo_id, exist_ok=True)pythontransformers
import os

import torch

from huggingface_hub import create_repo, upload_folder
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    GenerationConfig,
    AutoConfig,
    pipeline,
    set_seed,
)

model_id = "tiiuae/falcon-mamba-7b"
repo_id = "yujiepan/falcon-mamba-tiny-random"
save_path = f"/tmp/{repo_id}"
os.system(f'rm -rf {save_path}')

config = AutoConfig.from_pretrained(model_id)
config.use_cache = True
config.num_hidden_layers = 2
config.hidden_size = 8
config.intermediate_size = 16
config.state_size = 8

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

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

set_seed(42)
num_params = 0
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        print(name, p.shape)
        torch.nn.init.uniform_(p, -0.5, 0.5)
        num_params += p.numel()
print("Total number of parameters:", num_params)
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!"))

# create_repo(repo_id, exist_ok=True)
# upload_folder(repo_id=repo_id, folder_path=save_path, repo_type='model')
create_repo(repo_id, exist_ok=True)pythontransformers
import os

import torch

from huggingface_hub import create_repo, upload_folder
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    GenerationConfig,
    AutoConfig,
    pipeline,
    set_seed,
)

model_id = "tiiuae/falcon-mamba-7b"
repo_id = "yujiepan/falcon-mamba-tiny-random"
save_path = f"/tmp/{repo_id}"
os.system(f'rm -rf {save_path}')

config = AutoConfig.from_pretrained(model_id)
config.use_cache = True
config.num_hidden_layers = 2
config.hidden_size = 8
config.intermediate_size = 16
config.state_size = 8

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

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

set_seed(42)
num_params = 0
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        print(name, p.shape)
        torch.nn.init.uniform_(p, -0.5, 0.5)
        num_params += p.numel()
print("Total number of parameters:", num_params)
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!"))

# create_repo(repo_id, exist_ok=True)
# upload_folder(repo_id=repo_id, folder_path=save_path, repo_type='model')
create_repo(repo_id, exist_ok=True)pythontransformers
import os

import torch

from huggingface_hub import create_repo, upload_folder
from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    GenerationConfig,
    AutoConfig,
    pipeline,
    set_seed,
)

model_id = "tiiuae/falcon-mamba-7b"
repo_id = "yujiepan/falcon-mamba-tiny-random"
save_path = f"/tmp/{repo_id}"
os.system(f'rm -rf {save_path}')

config = AutoConfig.from_pretrained(model_id)
config.use_cache = True
config.num_hidden_layers = 2
config.hidden_size = 8
config.intermediate_size = 16
config.state_size = 8

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

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

set_seed(42)
num_params = 0
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        print(name, p.shape)
        torch.nn.init.uniform_(p, -0.5, 0.5)
        num_params += p.numel()
print("Total number of parameters:", num_params)
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!"))

# create_repo(repo_id, exist_ok=True)
# upload_folder(repo_id=repo_id, folder_path=save_path, repo_type='model')

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.