From: <huggingface.co/unsloth> Newsgroups: alt.freeweights.llamaSubject: tinyllama-chat-bnb-4bit Date: 2026-11-15Commit: effb5dcSigned: 2DC28CC7B26A283B ✓ Text generation model with 1.1B parameters. Safetensors weights, 765 MB in all. Published by unsloth under Apache-2.0.
1.1B params 765 MB tinyllama-chat-bnb-4bit safetensors permissive Facts Params 1.1B Size 765 MB Formats safetensors Task text generation License Apache-2.0 permissive
fw
$ fw get unsloth/tinyllama-chat-bnb-4bit
# manifest sha256 5cc7f1971f81… · 765 MB · 9 files
$ fw verify ./tinyllama-chat-bnb-4bit unsloth/tinyllama-chat-bnb-4bitHosted (signed) unsloth/tinyllama-chat-bnb-4bit Last check: 2026-11-15 03:25 UTC
Get help: custom fine-tune or private deploy. We review your setup before we quote.
Works with
Runs with Ranked by fit to this model (safetensors), then by GitHub stars.
Show all 24 Fine-tune with Show all 29
Overview
Size 765 MB
Weights 762 MB (safetensors)
Parameters 1.1B
Formats safetensors
Task text generation
License Apache-2.0 (permissive)
Files 9, each with a sha256
Publisher unsloth
Added 2026-11-15
Section alt.freeweights.llama Lineage
Original release from the publisher.
Where these bytes come from
Publisher at the pinned commit →You
Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge Host Last check Result huggingface.co 2026-11-15 03:25 UTC passed
Model card From the publisher at commit
effb5dc . Shown as plain text with links; images open at the publisher.
Files 9 files · 765 MB Weights 762 MB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256 File Size sha256 .gitattributes 1.52 KB 11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361 README.md 2.93 KB 3a4ae3d78036882f7ec0b0e93cfb023c003db6d4e29d0d22676c2a86211c70e7 config.json 1.24 KB 0b07d0e4ade1bc8467dac87e841a2f976edf9b00ab4453c2ba9b2d4780f2f97c generation_config.json 124 B d677ece3c7c89ed17316eed20261ad0364097e2314d7636ebe7cb0d8b67ca453 model.safetensors 762 MB 1217df46e04327e655b77ec52d85d27d107a83b17bb69187b329da82c35dc7f3 special_tokens_map.json 438 B 719833ff26ac897a3ec8ed946028a135de2a351470af59b4008744ab1f0ee9b7 tokenizer.json 1.84 MB bf467c9e0f536bda271283c6ef85eb1a943e3196b621c8a912d64953b205df83 tokenizer.model 500 KB 9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer_config.json 1.37 KB 120bdeef4ef95d5c173341250e5bba3e6533164299ba3e79395dcb255aa44629
Versions Each time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commit Date Contents effb5dc824 pinned now 2026-11-15 03:25 UTC 9 files · 765 MB
Use it fw
$ fw get unsloth/tinyllama-chat-bnb-4bit
# manifest sha256 5cc7f1971f81… · 765 MB · 9 files
$ fw verify ./tinyllama-chat-bnb-4bit unsloth/tinyllama-chat-bnb-4bitfw.py Checks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/tinyllama-chat-bnb-4bit.json --dir ./tinyllama-chat-bnb-4bit
$ python3 fw.py verify ./tinyllama-chat-bnb-4bit ./unsloth__tinyllama-chat-bnb-4bit.jsonhf The Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT =https://freeweights.allternit.com hf download unsloth/tinyllama-chat-bnb-4bit --revision effb5dc8248c9270b0db975639c17084417180a7 --local-dir ./tinyllama-chat-bnb-4bittransformers Load the weights in Python.
import os
os.environ["HF_ENDPOINT" ] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("unsloth/tinyllama-chat-bnb-4bit", revision="effb5dc8248c9270b0db975639c17084417180a7")
model = AutoModelForCausalLM.from_pretrained("unsloth/tinyllama-chat-bnb-4bit", revision="effb5dc8248c9270b0db975639c17084417180a7", device_map="auto")vLLM Serve an OpenAI-compatible API.
$ HF_ENDPOINT =https://freeweights.allternit.com vllm serve unsloth/tinyllama-chat-bnb-4bit --revision effb5dc8248c9270b0db975639c17084417180a7License Name Apache License 2.0 Id Apache-2.0 Class Permissive Redistribution yes Listing Hosted (signed) Decided License as declared by the publisher. No person read it. 2026-11-15 Text in README.md Text sha256 3a4ae3d78036882f7ec0b0e93cfb023c003db6d4e29d0d22676c2a86211c70e7 Terms gate No extra terms beyond the license. Read the license text
Licenses are checked against the license table . A custom license passes only after a person reads it.
Provenance From: <huggingface.co/unsloth> Newsgroups: alt.freeweights.llamaSubject: tinyllama-chat-bnb-4bit Date: 2026-11-15Commit: effb5dcSigned: 2DC28CC7B26A283B ✓ Upstream unsloth/tinyllama-chat-bnb-4bit Pinned commit effb5dc8248c9270b0db975639c17084417180a7 Manifest tinyllama-chat-bnb-4bit.json · .minisig Manifest sha256 5cc7f1971f81aac604b047ca13d01bad4d3c774da11d32fed834609165af41f4 Signature minisign, Ed25519, key 2DC28CC7B26A283B Created 2026-11-15 03:25 UTC Generator freeweights-manifest/0.1.0 Takedowns None. How to verify
$ curl -O https://freeweights.allternit.com/manifests/unsloth/tinyllama-chat-bnb-4bit.json
$ curl -O https://freeweights.allternit.com/manifests/unsloth/tinyllama-chat-bnb-4bit.json.minisig
$ minisign -Vm tinyllama-chat-bnb-4bit.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file> # compare with the Files tab A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download
Model tree No related models in this catalog. Nothing here lists this model as its parent, and it names no parent.
Get it
$ HF_ENDPOINT =https://freeweights.allternit.com hf download unsloth/tinyllama-chat-bnb-4bitOpen in Freeweights Studio Pull, verify and run it in the Allternit app on Desktop, web or phone.
8.5B params 17.0 GB Bunny-Llama-3-8B-V safetensors permissive Facts Params 8.5B Size 17.0 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/BAAI> Subject: Bunny-Llama-3-8B-V llama 21.9 GB Bunny-Llama-3-8B-V-gguf gguf permissive Facts Params not stated Size 21.9 GB Formats gguf Task not tagged License Apache-2.0 permissive flip From: <huggingface.co/BAAI> Subject: Bunny-Llama-3-8B-V-gguf 8.5B params 17.0 GB Bunny-v1_1-Llama-3-8B-V safetensors permissive Facts Params 8.5B Size 17.0 GB Formats safetensors Task image text to text License Apache-2.0 permissive flip From: <huggingface.co/BAAI> Subject: Bunny-v1_1-Llama-3-8B-V 6.7B params 13.5 GB codellama-7b safetensors permissive Facts Params 6.7B Size 13.5 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: codellama-7b 6.9B params 3.87 GB codellama-7b-bnb-4bit safetensors permissive Facts Params 6.9B Size 3.87 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/unsloth> Subject: codellama-7b-bnb-4bit 70.6B params 141 GB Infinity-Instruct-3M-0613-Llama3-70B safetensors permissive Facts Params 70.6B Size 141 GB Formats safetensors Task text generation License Apache-2.0 permissive flip From: <huggingface.co/BAAI> Subject: Infinity-Instruct-3M-0613-Llama3-70B
unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.llamaSubject: 
BAAI