Instructions to use tensorblock/bloom-3b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/bloom-3b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/bloom-3b-GGUF",
	filename="bloom-3b-Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/bloom-3b-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/bloom-3b-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/bloom-3b-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/bloom-3b-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/bloom-3b-GGUF:Q2_K

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tensorblock/bloom-3b-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/bloom-3b-GGUF:Q2_K

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tensorblock/bloom-3b-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/bloom-3b-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/bloom-3b-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/bloom-3b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/bloom-3b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/bloom-3b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorblock/bloom-3b-GGUF:Q2_K

Ollama
How to use tensorblock/bloom-3b-GGUF with Ollama:
```
ollama run hf.co/tensorblock/bloom-3b-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/bloom-3b-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tensorblock/bloom-3b-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tensorblock/bloom-3b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/bloom-3b-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tensorblock/bloom-3b-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/bloom-3b-GGUF:Q2_K
```

Lemonade

How to use tensorblock/bloom-3b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/bloom-3b-GGUF:Q2_K

Run and chat with the model

lemonade run user.bloom-3b-GGUF-Q2_K

List all available models

lemonade list

bloom-3b-GGUF / README.md

morriszms

Update README.md

aa4620d verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

42.1 kB

	---
	license: bigscience-bloom-rail-1.0
	language:
	- ak
	- ar
	- as
	- bm
	- bn
	- ca
	- code
	- en
	- es
	- eu
	- fon
	- fr
	- gu
	- hi
	- id
	- ig
	- ki
	- kn
	- lg
	- ln
	- ml
	- mr
	- ne
	- nso
	- ny
	- or
	- pa
	- pt
	- rn
	- rw
	- sn
	- st
	- sw
	- ta
	- te
	- tn
	- ts
	- tum
	- tw
	- ur
	- vi
	- wo
	- xh
	- yo
	- zh
	- zhs
	- zht
	- zu
	pipeline_tag: text-generation
	tags:
	- TensorBlock
	- GGUF
	base_model: bigscience/bloom-3b
	model-index:
	- name: bloom
	results:
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: arc_challenge
	type: arc_challenge
	metrics:
	- type: acc
	value: 0.27986348122866894
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: arc_easy
	type: arc_easy
	metrics:
	- type: acc
	value: 0.5946969696969697
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: axb
	type: axb
	metrics:
	- type: acc
	value: 0.4433876811594203
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: axg
	type: axg
	metrics:
	- type: acc
	value: 0.5
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: boolq
	type: boolq
	metrics:
	- type: acc
	value: 0.6165137614678899
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: cb
	type: cb
	metrics:
	- type: acc
	value: 0.30357142857142855
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: cola
	type: cola
	metrics:
	- type: acc
	value: 0.610738255033557
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: copa
	type: copa
	metrics:
	- type: acc
	value: 0.63
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: crows_pairs_english
	type: crows_pairs_english
	metrics:
	- type: acc
	value: 0.4973166368515206
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: crows_pairs_french
	type: crows_pairs_french
	metrics:
	- type: acc
	value: 0.5032796660703638
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: diabla
	type: diabla
	metrics:
	- type: acc
	value: 0.28888308977035493
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_afr
	type: gsarti/flores_101_afr
	metrics:
	- type: byte_perplexity
	value: 6.500798737976343
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_amh
	type: gsarti/flores_101_amh
	metrics:
	- type: byte_perplexity
	value: 3.9726863338897145
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ara
	type: gsarti/flores_101_ara
	metrics:
	- type: byte_perplexity
	value: 1.8083841089875814
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_asm
	type: gsarti/flores_101_asm
	metrics:
	- type: byte_perplexity
	value: 5.699102962086425
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ast
	type: gsarti/flores_101_ast
	metrics:
	- type: byte_perplexity
	value: 3.9252047073429384
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_azj
	type: gsarti/flores_101_azj
	metrics:
	- type: byte_perplexity
	value: 6.942805054270002
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_bel
	type: gsarti/flores_101_bel
	metrics:
	- type: byte_perplexity
	value: 3.614136245847082
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ben
	type: gsarti/flores_101_ben
	metrics:
	- type: byte_perplexity
	value: 5.121491534300969
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_bos
	type: gsarti/flores_101_bos
	metrics:
	- type: byte_perplexity
	value: 5.653353469118798
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_bul
	type: gsarti/flores_101_bul
	metrics:
	- type: byte_perplexity
	value: 2.7014693938055068
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_cat
	type: gsarti/flores_101_cat
	metrics:
	- type: byte_perplexity
	value: 2.305190041967345
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ceb
	type: gsarti/flores_101_ceb
	metrics:
	- type: byte_perplexity
	value: 6.291000321323428
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ces
	type: gsarti/flores_101_ces
	metrics:
	- type: byte_perplexity
	value: 5.447322753586386
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ckb
	type: gsarti/flores_101_ckb
	metrics:
	- type: byte_perplexity
	value: 3.7255124939234765
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_cym
	type: gsarti/flores_101_cym
	metrics:
	- type: byte_perplexity
	value: 12.539424151448149
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_dan
	type: gsarti/flores_101_dan
	metrics:
	- type: byte_perplexity
	value: 5.183309001005672
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_deu
	type: gsarti/flores_101_deu
	metrics:
	- type: byte_perplexity
	value: 3.1180422286591347
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ell
	type: gsarti/flores_101_ell
	metrics:
	- type: byte_perplexity
	value: 2.467943456164706
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_eng
	type: gsarti/flores_101_eng
	metrics:
	- type: byte_perplexity
	value: 2.018740628193298
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_est
	type: gsarti/flores_101_est
	metrics:
	- type: byte_perplexity
	value: 9.11654425176368
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_fas
	type: gsarti/flores_101_fas
	metrics:
	- type: byte_perplexity
	value: 3.058009097116482
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_fin
	type: gsarti/flores_101_fin
	metrics:
	- type: byte_perplexity
	value: 6.847047959628553
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_fra
	type: gsarti/flores_101_fra
	metrics:
	- type: byte_perplexity
	value: 1.9975177011840075
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ful
	type: gsarti/flores_101_ful
	metrics:
	- type: byte_perplexity
	value: 11.465912731488828
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_gle
	type: gsarti/flores_101_gle
	metrics:
	- type: byte_perplexity
	value: 8.681491663539422
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_glg
	type: gsarti/flores_101_glg
	metrics:
	- type: byte_perplexity
	value: 3.029991089015508
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_guj
	type: gsarti/flores_101_guj
	metrics:
	- type: byte_perplexity
	value: 4.955224230286231
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_hau
	type: gsarti/flores_101_hau
	metrics:
	- type: byte_perplexity
	value: 10.758347356372159
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_heb
	type: gsarti/flores_101_heb
	metrics:
	- type: byte_perplexity
	value: 3.6004478129801667
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_hin
	type: gsarti/flores_101_hin
	metrics:
	- type: byte_perplexity
	value: 4.712530650588064
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_hrv
	type: gsarti/flores_101_hrv
	metrics:
	- type: byte_perplexity
	value: 5.822418943372185
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_hun
	type: gsarti/flores_101_hun
	metrics:
	- type: byte_perplexity
	value: 6.440482646965992
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_hye
	type: gsarti/flores_101_hye
	metrics:
	- type: byte_perplexity
	value: 3.657718918347166
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ibo
	type: gsarti/flores_101_ibo
	metrics:
	- type: byte_perplexity
	value: 5.564814003872672
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ind
	type: gsarti/flores_101_ind
	metrics:
	- type: byte_perplexity
	value: 2.1597101468869373
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_isl
	type: gsarti/flores_101_isl
	metrics:
	- type: byte_perplexity
	value: 8.082349269518136
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ita
	type: gsarti/flores_101_ita
	metrics:
	- type: byte_perplexity
	value: 2.9687591414176207
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_jav
	type: gsarti/flores_101_jav
	metrics:
	- type: byte_perplexity
	value: 7.0573805415708994
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_jpn
	type: gsarti/flores_101_jpn
	metrics:
	- type: byte_perplexity
	value: 2.7758864197116933
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_kam
	type: gsarti/flores_101_kam
	metrics:
	- type: byte_perplexity
	value: 11.072949642861332
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_kan
	type: gsarti/flores_101_kan
	metrics:
	- type: byte_perplexity
	value: 5.551730651007082
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_kat
	type: gsarti/flores_101_kat
	metrics:
	- type: byte_perplexity
	value: 2.522630524283745
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_kaz
	type: gsarti/flores_101_kaz
	metrics:
	- type: byte_perplexity
	value: 3.3901748516975574
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_kea
	type: gsarti/flores_101_kea
	metrics:
	- type: byte_perplexity
	value: 8.918534182590863
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_kir
	type: gsarti/flores_101_kir
	metrics:
	- type: byte_perplexity
	value: 3.729278369847201
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_kor
	type: gsarti/flores_101_kor
	metrics:
	- type: byte_perplexity
	value: 3.932884847226212
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_lao
	type: gsarti/flores_101_lao
	metrics:
	- type: byte_perplexity
	value: 2.9077314760849924
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_lav
	type: gsarti/flores_101_lav
	metrics:
	- type: byte_perplexity
	value: 7.777221919194806
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_lin
	type: gsarti/flores_101_lin
	metrics:
	- type: byte_perplexity
	value: 7.524842908050988
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_lit
	type: gsarti/flores_101_lit
	metrics:
	- type: byte_perplexity
	value: 7.369179434621725
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ltz
	type: gsarti/flores_101_ltz
	metrics:
	- type: byte_perplexity
	value: 8.801059747949214
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_lug
	type: gsarti/flores_101_lug
	metrics:
	- type: byte_perplexity
	value: 8.483203026364786
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_luo
	type: gsarti/flores_101_luo
	metrics:
	- type: byte_perplexity
	value: 11.975963093623681
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_mal
	type: gsarti/flores_101_mal
	metrics:
	- type: byte_perplexity
	value: 4.615948455160037
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_mar
	type: gsarti/flores_101_mar
	metrics:
	- type: byte_perplexity
	value: 5.483253482821379
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_mkd
	type: gsarti/flores_101_mkd
	metrics:
	- type: byte_perplexity
	value: 2.9656732291754087
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_mlt
	type: gsarti/flores_101_mlt
	metrics:
	- type: byte_perplexity
	value: 15.004773437665275
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_mon
	type: gsarti/flores_101_mon
	metrics:
	- type: byte_perplexity
	value: 3.410598542315402
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_mri
	type: gsarti/flores_101_mri
	metrics:
	- type: byte_perplexity
	value: 7.474035895661322
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_msa
	type: gsarti/flores_101_msa
	metrics:
	- type: byte_perplexity
	value: 2.5710001772665634
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_mya
	type: gsarti/flores_101_mya
	metrics:
	- type: byte_perplexity
	value: 2.413577969878331
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_nld
	type: gsarti/flores_101_nld
	metrics:
	- type: byte_perplexity
	value: 4.127831721885065
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_nob
	type: gsarti/flores_101_nob
	metrics:
	- type: byte_perplexity
	value: 5.402763169129877
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_npi
	type: gsarti/flores_101_npi
	metrics:
	- type: byte_perplexity
	value: 5.199342701937889
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_nso
	type: gsarti/flores_101_nso
	metrics:
	- type: byte_perplexity
	value: 8.154626800955667
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_nya
	type: gsarti/flores_101_nya
	metrics:
	- type: byte_perplexity
	value: 8.179860208369393
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_oci
	type: gsarti/flores_101_oci
	metrics:
	- type: byte_perplexity
	value: 4.8617357393685845
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_orm
	type: gsarti/flores_101_orm
	metrics:
	- type: byte_perplexity
	value: 12.911595421079408
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ory
	type: gsarti/flores_101_ory
	metrics:
	- type: byte_perplexity
	value: 5.189421861225964
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_pan
	type: gsarti/flores_101_pan
	metrics:
	- type: byte_perplexity
	value: 4.698477289331806
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_pol
	type: gsarti/flores_101_pol
	metrics:
	- type: byte_perplexity
	value: 4.625550458479643
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_por
	type: gsarti/flores_101_por
	metrics:
	- type: byte_perplexity
	value: 1.9754515986213523
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_pus
	type: gsarti/flores_101_pus
	metrics:
	- type: byte_perplexity
	value: 4.4963371422771585
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ron
	type: gsarti/flores_101_ron
	metrics:
	- type: byte_perplexity
	value: 4.965456830031304
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_rus
	type: gsarti/flores_101_rus
	metrics:
	- type: byte_perplexity
	value: 2.0498020542445303
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_slk
	type: gsarti/flores_101_slk
	metrics:
	- type: byte_perplexity
	value: 6.450822127057479
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_slv
	type: gsarti/flores_101_slv
	metrics:
	- type: byte_perplexity
	value: 6.620252120186232
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_sna
	type: gsarti/flores_101_sna
	metrics:
	- type: byte_perplexity
	value: 8.462166771382726
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_snd
	type: gsarti/flores_101_snd
	metrics:
	- type: byte_perplexity
	value: 5.466066951221973
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_som
	type: gsarti/flores_101_som
	metrics:
	- type: byte_perplexity
	value: 11.95918054093392
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_spa
	type: gsarti/flores_101_spa
	metrics:
	- type: byte_perplexity
	value: 1.8965140104323535
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_srp
	type: gsarti/flores_101_srp
	metrics:
	- type: byte_perplexity
	value: 2.871214785885079
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_swe
	type: gsarti/flores_101_swe
	metrics:
	- type: byte_perplexity
	value: 5.054972008155866
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_swh
	type: gsarti/flores_101_swh
	metrics:
	- type: byte_perplexity
	value: 3.6973091886730676
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_tam
	type: gsarti/flores_101_tam
	metrics:
	- type: byte_perplexity
	value: 4.539493400469833
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_tel
	type: gsarti/flores_101_tel
	metrics:
	- type: byte_perplexity
	value: 5.807499987508966
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_tgk
	type: gsarti/flores_101_tgk
	metrics:
	- type: byte_perplexity
	value: 3.5994818827380426
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_tgl
	type: gsarti/flores_101_tgl
	metrics:
	- type: byte_perplexity
	value: 5.667053833119858
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_tha
	type: gsarti/flores_101_tha
	metrics:
	- type: byte_perplexity
	value: 2.365940201944242
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_tur
	type: gsarti/flores_101_tur
	metrics:
	- type: byte_perplexity
	value: 4.885014749844601
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_ukr
	type: gsarti/flores_101_ukr
	metrics:
	- type: byte_perplexity
	value: 2.7240934990288483
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_umb
	type: gsarti/flores_101_umb
	metrics:
	- type: byte_perplexity
	value: 12.766915508610673
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_urd
	type: gsarti/flores_101_urd
	metrics:
	- type: byte_perplexity
	value: 1.9797467071381232
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_uzb
	type: gsarti/flores_101_uzb
	metrics:
	- type: byte_perplexity
	value: 12.002337637722146
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_vie
	type: gsarti/flores_101_vie
	metrics:
	- type: byte_perplexity
	value: 1.76578415476397
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_wol
	type: gsarti/flores_101_wol
	metrics:
	- type: byte_perplexity
	value: 9.144285650306488
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_xho
	type: gsarti/flores_101_xho
	metrics:
	- type: byte_perplexity
	value: 7.403240538286952
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_yor
	type: gsarti/flores_101_yor
	metrics:
	- type: byte_perplexity
	value: 5.91272037551173
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_zho_simpl
	type: gsarti/flores_101_zho_simpl
	metrics:
	- type: byte_perplexity
	value: 2.2769070822768533
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_zho_trad
	type: gsarti/flores_101_zho_trad
	metrics:
	- type: byte_perplexity
	value: 2.5180582198242383
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: gsarti/flores_101_zul
	type: gsarti/flores_101_zul
	metrics:
	- type: byte_perplexity
	value: 8.53353320693145
	name: byte_perplexity
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: headqa
	type: headqa
	metrics:
	- type: acc
	value: 0.26440554339897887
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: hellaswag
	type: hellaswag
	metrics:
	- type: acc
	value: 0.41236805417247563
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: logiqa
	type: logiqa
	metrics:
	- type: acc
	value: 0.2073732718894009
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: mathqa
	type: mathqa
	metrics:
	- type: acc
	value: 0.24958123953098826
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: mc_taco
	type: mc_taco
	metrics:
	- type: em
	value: 0.11936936936936937
	name: em
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: mnli
	type: mnli
	metrics:
	- type: acc
	value: 0.35496688741721855
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: mnli_mismatched
	type: mnli_mismatched
	metrics:
	- type: acc
	value: 0.35211554109031734
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: mrpc
	type: mrpc
	metrics:
	- type: acc
	value: 0.5857843137254902
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: multirc
	type: multirc
	metrics:
	- type: acc
	value: 0.5375412541254125
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: openbookqa
	type: openbookqa
	metrics:
	- type: acc
	value: 0.216
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: piqa
	type: piqa
	metrics:
	- type: acc
	value: 0.7078346028291621
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: prost
	type: prost
	metrics:
	- type: acc
	value: 0.22683603757472245
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: pubmedqa
	type: pubmedqa
	metrics:
	- type: acc
	value: 0.616
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: qnli
	type: qnli
	metrics:
	- type: acc
	value: 0.5072304594545122
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: qqp
	type: qqp
	metrics:
	- type: acc
	value: 0.3842443729903537
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: race
	type: race
	metrics:
	- type: acc
	value: 0.3521531100478469
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: rte
	type: rte
	metrics:
	- type: acc
	value: 0.47653429602888087
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: sciq
	type: sciq
	metrics:
	- type: acc
	value: 0.892
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: sst
	type: sst
	metrics:
	- type: acc
	value: 0.5177752293577982
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: triviaqa
	type: triviaqa
	metrics:
	- type: acc
	value: 0.041633518960487934
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: tydiqa_primary
	type: tydiqa_primary
	metrics:
	- type: acc
	value: 0.3011337608795236
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: webqs
	type: webqs
	metrics:
	- type: acc
	value: 0.01673228346456693
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: wic
	type: wic
	metrics:
	- type: acc
	value: 0.5015673981191222
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: winogrande
	type: winogrande
	metrics:
	- type: acc
	value: 0.5864246250986582
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: wnli
	type: wnli
	metrics:
	- type: acc
	value: 0.471830985915493
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: wsc
	type: wsc
	metrics:
	- type: acc
	value: 0.4423076923076923
	name: acc
	verified: false
	- task:
	type: text-generation
	name: text generation
	dataset:
	name: humaneval
	type: humaneval
	metrics:
	- type: pass@1
	value: 0.15524390243902436
	name: pass@1
	verified: false
	- type: pass@10
	value: 0.3220367632383857
	name: pass@10
	verified: false
	- type: pass@100
	value: 0.5545431515723145
	name: pass@100
	verified: false
	---

	<div style="width: auto; margin-left: auto; margin-right: auto">
	<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
	</div>

	[![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)
	[![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)
	[![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)
	[![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)
	[![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)


	## bigscience/bloom-3b - GGUF

	This repo contains GGUF format model files for [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b).

	The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).


	## Our projects
	<table border="1" cellspacing="0" cellpadding="10">
	<tr>
	<th colspan="2" style="font-size: 25px;">Forge</th>
	</tr>
	<tr>
	<th colspan="2">
	<img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
	</th>
	</tr>
	<tr>
	<th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
	</tr>
	<tr>
	<th colspan="2">
	<a href="https://github.com/TensorBlock/forge" target="_blank" style="
	display: inline-block;
	padding: 8px 16px;
	background-color: #FF7F50;
	color: white;
	text-decoration: none;
	border-radius: 6px;
	font-weight: bold;
	font-family: sans-serif;
	">🚀 Try it now! 🚀</a>
	</th>
	</tr>

	<tr>
	<th style="font-size: 25px;">Awesome MCP Servers</th>
	<th style="font-size: 25px;">TensorBlock Studio</th>
	</tr>
	<tr>
	<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
	<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
	</tr>
	<tr>
	<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
	<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
	</tr>
	<tr>
	<th>
	<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
	display: inline-block;
	padding: 8px 16px;
	background-color: #FF7F50;
	color: white;
	text-decoration: none;
	border-radius: 6px;
	font-weight: bold;
	font-family: sans-serif;
	">👀 See what we built 👀</a>
	</th>
	<th>
	<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
	display: inline-block;
	padding: 8px 16px;
	background-color: #FF7F50;
	color: white;
	text-decoration: none;
	border-radius: 6px;
	font-weight: bold;
	font-family: sans-serif;
	">👀 See what we built 👀</a>
	</th>
	</tr>
	</table>
	## Prompt template


	```

	```

	## Model file specification

	\| Filename \| Quant type \| File Size \| Description \|
	\| -------- \| ---------- \| --------- \| ----------- \|
	\| [bloom-3b-Q2_K.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q2_K.gguf) \| Q2_K \| 1.516 GB \| smallest, significant quality loss - not recommended for most purposes \|
	\| [bloom-3b-Q3_K_S.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q3_K_S.gguf) \| Q3_K_S \| 1.707 GB \| very small, high quality loss \|
	\| [bloom-3b-Q3_K_M.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q3_K_M.gguf) \| Q3_K_M \| 1.905 GB \| very small, high quality loss \|
	\| [bloom-3b-Q3_K_L.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q3_K_L.gguf) \| Q3_K_L \| 2.016 GB \| small, substantial quality loss \|
	\| [bloom-3b-Q4_0.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q4_0.gguf) \| Q4_0 \| 2.079 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \|
	\| [bloom-3b-Q4_K_S.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q4_K_S.gguf) \| Q4_K_S \| 2.088 GB \| small, greater quality loss \|
	\| [bloom-3b-Q4_K_M.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q4_K_M.gguf) \| Q4_K_M \| 2.235 GB \| medium, balanced quality - recommended \|
	\| [bloom-3b-Q5_0.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q5_0.gguf) \| Q5_0 \| 2.428 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \|
	\| [bloom-3b-Q5_K_S.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q5_K_S.gguf) \| Q5_K_S \| 2.428 GB \| large, low quality loss - recommended \|
	\| [bloom-3b-Q5_K_M.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q5_K_M.gguf) \| Q5_K_M \| 2.546 GB \| large, very low quality loss - recommended \|
	\| [bloom-3b-Q6_K.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q6_K.gguf) \| Q6_K \| 2.799 GB \| very large, extremely low quality loss \|
	\| [bloom-3b-Q8_0.gguf](https://huggingface.co/tensorblock/bloom-3b-GGUF/blob/main/bloom-3b-Q8_0.gguf) \| Q8_0 \| 3.621 GB \| very large, extremely low quality loss - not recommended \|


	## Downloading instruction

	### Command line

	Firstly, install Huggingface Client

	```shell
	pip install -U "huggingface_hub[cli]"
	```

	Then, downoad the individual model file the a local directory

	```shell
	huggingface-cli download tensorblock/bloom-3b-GGUF --include "bloom-3b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
	```

	If you wanna download multiple model files with a pattern (e.g., `Q4_Kgguf`), you can try:

	```shell
	huggingface-cli download tensorblock/bloom-3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='Q4_Kgguf'
	```