TinyLlama-1.1B-Chat-v1.0 is a large language model released by community (TinyLlama project), released under the Apache-2.0 license, with a claimed knowledge cutoff of 2024-01-04. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.
Description
Community project training a compact 1.1B Llama-architecture model on 3 trillion tokens, notable for demonstrating small-model viability with heavy overtraining.
Metadata
Hugging Face stats
1,402,430 downloads on Hugging Face · 1,819 likes · pipeline: text-generation · library: transformers
Weight Hashes
Weights file
SHA-2566e6001da2106d4757498752a021df6c2bdc332c650aae4bae6b0c004dcf14933
SHA3-2567a11444981196799af49f2b9a1a26f54e7885d297230c65035ef12398722ba30
BLAKE3684041cd46bfafc7eae1342055f721071c00193189c00818298ab5cdec835a7b
Config file
SHA-256486bedda3a6988332e60d9638a09ca4b260d34ebcf1b19e22cf3b140b63d8fe9
SHA3-2565247ac6781d260fbb09862f298724392e7bd275c9ea882bbc85023abc1d6a044
BLAKE3b794ef667d9c5bbd46d4c47cc511ac68d958389e7b39f4f78aa41be8e4bfe7ee
Tokenizer file
SHA-256bcd04f0eadf90287bd26e1a183ac487d8a141b09b06aecb7725bbdd343640f2e
SHA3-2567c2d7b488de143d8999c691c8f43b44d8191ea9df441070b0ec9c39575ffc0f1
BLAKE372ac17c8276fd296d37c6c556251d0e31a6fdc897478fb3dd725cd25841ed1c6
Verify it yourself
curl -L -o "model.safetensors" "https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0/resolve/fe8a4ea1ffedaf415f4da2f062534de366a451e6/model.safetensors" sha256sum "model.safetensors"
Expected SHA-256: 6e6001da2106d4757498752a021df6c2bdc332c650aae4bae6b0c004dcf14933