CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.llama / llama-2-7b-bnb-4bit
From: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.llamaSubject:

llama-2-7b-bnb-4bit

Date: 2026-11-15Commit: d3a9fcbSigned: 2DC28CC7B26A283B ✓

Text generation model with 6.9B parameters. Safetensors weights, 3.87 GB in all. Published by unsloth under Apache-2.0.

6.9B params3.87GBllama-2-7b-bnb-4bitsafetensorspermissive
FactsParams6.9BSize3.87 GBFormatssafetensorsTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get unsloth/llama-2-7b-bnb-4bit
# manifest sha256 d35f6d591eb5… · 3.87 GB · 9 files
$ fw verify ./llama-2-7b-bnb-4bit unsloth/llama-2-7b-bnb-4bit
From sourceHosted (signed)unsloth/llama-2-7b-bnb-4bitLast check: 2026-11-15 03:25 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Works with

Run24Fine-tune29Convert15Evaluate13Scan13Apps58
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
3.87 GB
Weights
3.87 GB (safetensors)
Parameters
6.9B
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
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 03:25 UTCpassed

Model card

From the publisher at commit d3a9fcb. Shown as plain text with links; images open at the publisher.

Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!#

Directly quantized 4bit model with bitsandbytes.

We have a Google Colab Tesla T4 notebook for Llama 7b here: https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing

https://discord.gg/u54VK8m8tk https://ko-fi.com/unsloth https://github.com/unslothai/unsloth

✨ Finetune for Free#

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supportsFree NotebooksPerformanceMemory use
Gemma 7b▶️ Start on Colab2.4x faster58% less
Mistral 7b▶️ Start on Colab2.2x faster62% less
Llama-2 7b▶️ Start on Colab2.2x faster43% less
TinyLlama▶️ Start on Colab3.9x faster74% less
CodeLlama 34b A100▶️ Start on Colab1.9x faster27% less
Mistral 7b 1xT4▶️ Start on Kaggle5x faster\*62% less
DPO - Zephyr▶️ Start on Colab1.9x faster19% less

Files

9 files · 3.87 GBWeights 3.87 GB (safetensors). Sizes and sha256 from the signed manifest.
Hide all 9 files with their sha256
FileSizesha256
.gitattributes1.52 KB11ad7efa24975ee4b0c3c3a38ed18737f0658a5f75a0a96787b576a78a023361
README.md3.13 KB256f3187325d2fd8138939c26f66ca3621e7fc5aadcb5d757cbbf4b37a84416b
config.json1.23 KBf9b8ae96191a4bb6aea9706480302d7f4923c77f46b0dde0a7af245b17981996
generation_config.json183 B07f7cbfd02476f674a83b83d5cb9c1efc9d480395255429b17943d4543cf6dca
model.safetensors3.87 GBbd12aa5433caa8df441f5c9a0ca376bc33d185d18fbb6ccdfbf55fbcbf15d542
special_tokens_map.json438 B719833ff26ac897a3ec8ed946028a135de2a351470af59b4008744ab1f0ee9b7
tokenizer.json1.84 MBbf467c9e0f536bda271283c6ef85eb1a943e3196b621c8a912d64953b205df83
tokenizer.model500 KB9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
tokenizer_config.json948 Bdf05b9bd5fba9b5be06565a864b9d66999d544a811a0f9f9e5cd163d885b04c4
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
d3a9fcb2d7 pinned now2026-11-15 03:25 UTC9 files · 3.87 GB

Use it

$ fw get unsloth/llama-2-7b-bnb-4bit
# manifest sha256 d35f6d591eb5… · 3.87 GB · 9 files
$ fw verify ./llama-2-7b-bnb-4bit unsloth/llama-2-7b-bnb-4bit
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/llama-2-7b-bnb-4bit.json --dir ./llama-2-7b-bnb-4bit $ python3 fw.py verify ./llama-2-7b-bnb-4bit ./unsloth__llama-2-7b-bnb-4bit.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/llama-2-7b-bnb-4bit --revision d3a9fcb2d76d5c4310c4f85652a4c67c94d9a119 --local-dir ./llama-2-7b-bnb-4bit
transformersLoad the weights in Python.
import os os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com" from transformers import AutoModelForCausalLM, AutoTokenizer tok = AutoTokenizer.from_pretrained("unsloth/llama-2-7b-bnb-4bit", revision="d3a9fcb2d76d5c4310c4f85652a4c67c94d9a119") model = AutoModelForCausalLM.from_pretrained("unsloth/llama-2-7b-bnb-4bit", revision="d3a9fcb2d76d5c4310c4f85652a4c67c94d9a119", device_map="auto")
vLLMServe an OpenAI-compatible API.
$ HF_ENDPOINT=https://freeweights.allternit.com vllm serve unsloth/llama-2-7b-bnb-4bit --revision d3a9fcb2d76d5c4310c4f85652a4c67c94d9a119
Run at home

License

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
256f3187325d2fd8138939c26f66ca3621e7fc5aadcb5d757cbbf4b37a84416b
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: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.llamaSubject: llama-2-7b-bnb-4bitDate: 2026-11-15Commit: d3a9fcbSigned: 2DC28CC7B26A283B ✓
Upstream
unsloth/llama-2-7b-bnb-4bit
Pinned commit
d3a9fcb2d76d5c4310c4f85652a4c67c94d9a119
Manifest
llama-2-7b-bnb-4bit.json · .minisig
Manifest sha256
d35f6d591eb539f65b4bb94f51fa7a74ba6349e167bfaaa4693b2adc759f8a3d
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/llama-2-7b-bnb-4bit.json $ curl -O https://freeweights.allternit.com/manifests/unsloth/llama-2-7b-bnb-4bit.json.minisig $ minisign -Vm llama-2-7b-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
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/llama-2-7b-bnb-4bit
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. llama-2-7b-bnb-4bit.json. Provenance. Takedown history: none.
Source
huggingface.co/unsloth/llama-2-7b-bnb-4bit

Related models

All of alt.freeweights.llama →
From: BAAI <huggingface.co/BAAI>Subject: Bunny-Llama-3-8B-V
From: BAAI <huggingface.co/BAAI>Subject: Bunny-Llama-3-8B-V-gguf
From: BAAI <huggingface.co/BAAI>Subject: Bunny-v1_1-Llama-3-8B-V
From: unsloth <huggingface.co/unsloth>Subject: codellama-7b
From: unsloth <huggingface.co/unsloth>Subject: codellama-7b-bnb-4bit
From: BAAI <huggingface.co/BAAI>Subject: Infinity-Instruct-3M-0613-Llama3-70B