Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
1212
11
Tom Jobbins
PRO
TheBloke
Follow
toats's profile picture
jsfs11's profile picture
vivalamovie's profile picture
19217 followers
·
16 following
TheBlokeAI
TheBloke
AI & ML interests
LLM: quantisation, fine tuning
Articles
Making LLMs lighter with AutoGPTQ and transformers
Aug 23, 2023
•
6
Organizations
TheBloke
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
New activity in
TheBloke/Llama-2-70B-GGUF
3 months ago
fix for join commands
1
#2 opened 3 months ago by
orbiter
New activity in
TheBloke/CodeLlama-70B-hf-AWQ
3 months ago
not codelama
3
#1 opened 3 months ago by
luckiskind
New activity in
TheBloke/MegaDolphin-120b-GPTQ
3 months ago
Missing files
2
#1 opened 3 months ago by
Danne980
New activity in
TheBloke/Fennec-Mixtral-8x7B-GGUF
4 months ago
Is this the same model with orangetin/OpenHermes-Mixtral-8x7B ?
2
#2 opened 4 months ago by
bingw5
New activity in
Yhyu13/LMCocktail-10.7B-v1
4 months ago
Quant pls
4
#1 opened 4 months ago by
Yhyu13
New activity in
VAGOsolutions/SauerkrautLM-SOLAR-Instruct
4 months ago
Quants uploading now
1
#4 opened 4 months ago by
TheBloke
New activity in
ddh0/OrcaMaidXL-17B-32k
4 months ago
Add YaRN modeling code
#1 opened 4 months ago by
TheBloke
New activity in
TheBloke/openchat-3.5-1210-AWQ
4 months ago
Update special_tokens_map.json
#1 opened 4 months ago by
alpayariyak
New activity in
TheBloke/openchat-3.5-1210-GPTQ
4 months ago
Update special_tokens_map.json
#1 opened 4 months ago by
alpayariyak
New activity in
TheBloke/Llama-2-13B-Chat-Dutch-AWQ
4 months ago
Update to new format and include chat template with default system message
#1 opened 4 months ago by
BramVanroy
New activity in
TheBloke/Llama-2-13B-Chat-Dutch-GPTQ
4 months ago
Update to new format and include chat template with default system message
#1 opened 4 months ago by
BramVanroy
New activity in
ddh0/Norocetacean-20b-10k
4 months ago
Update configuration_llama.py, required to get model to Load as `rope_scaling` needs to be None, or else a dictionary
#1 opened 4 months ago by
TheBloke
New activity in
TheBloke/Rogue-Rose-103b-v0.2-GPTQ
4 months ago
Missing Model
1
#1 opened 4 months ago by
Razzor9000
New activity in
Undi95/Mixtral-8x7B-MoE-RP-Story
4 months ago
Model config.json has Mistral params instead of Mixtral, breaking ExLlama quants and maybe affecting others too
#3 opened 4 months ago by
TheBloke
New activity in
TheBloke/SOLAR-10.7B-Instruct-v1.0-GGUF
4 months ago
vocabulary maybe wrong
3
#1 opened 4 months ago by
limoncc
New activity in
TheBloke/openchat-3.5-1210-GGUF
4 months ago
Sorta Broken
6
#1 opened 4 months ago by
dillfrescott
New activity in
TheBloke/Mixtral-8x7B-v0.1-GPTQ
4 months ago
RuntimeError: shape '[32, 8]' is invalid for input of size 0
7
#5 opened 4 months ago by
woldeM
New activity in
mattshumer/mistral-8x7b-chat
4 months ago
Quant pls
1
#5 opened 5 months ago by
Yhyu13
New activity in
TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ
4 months ago
Did anyone get it to run?
11
#1 opened 5 months ago by
dimaischenko
New activity in
TheBlokeAI/Mixtral-tiny-GPTQ
4 months ago
Seems like the GPTQ versions are broken
4
#2 opened 4 months ago by
NePe
What is this model?
3
#1 opened 5 months ago by
Yuuru
New activity in
TheBloke/Qwen-14B-Chat-AWQ
5 months ago
Which calibration set is chose?
4
#4 opened 5 months ago by
frankxyy
New activity in
TheBloke/Mixtral-8x7B-v0.1-GGUF
5 months ago
Other quant types.
2
#1 opened 5 months ago by
dog3-l0ver
It works.
6
#3 opened 5 months ago by
Yuuru
For the time being that mode with unofficial llamacpp works terrible - bad bad in answering - Instruct version is the best all of llm ever so far.
3
#5 opened 5 months ago by
mirek190
New activity in
TheBloke/Marcoroni-7B-v3-GGUF
5 months ago
The original model has a fixed an issue, please update it
1
#1 opened 5 months ago by
Hoioi
New activity in
TheBloke/NexusRaven-V2-13B-GGUF
5 months ago
Could you please help change the license?
2
#1 opened 5 months ago by
banghua
New activity in
TheBloke/go-bruins-v2-GGUF
5 months ago
It generates <0x0A> instead of new line
4
#1 opened 5 months ago by
Hoioi
New activity in
rwitz/go-bruins-v2
5 months ago
uses <0x0A> instead of the actual end of line
5
#6 opened 5 months ago by
jasonmbrown
New activity in
nsfwthrowitaway69/Venus-103b-v1.1
5 months ago
GGUF quants
1
#3 opened 5 months ago by
OrangeApples
New activity in
TheBloke/DiscoLM-mixtral-8x7b-v2-GPTQ
5 months ago
What model is this?
2
#1 opened 5 months ago by
rjmehta
New activity in
TheBloke/Mistral-7B-Instruct-v0.1-GGUF
5 months ago
Corrected the Chat template
#17 opened 5 months ago by
SalmanFaroz
New activity in
TheBloke/Magicoder-S-DS-6.7B-GGUF
5 months ago
failed to load the model
16
#1 opened 5 months ago by
rinoa
New activity in
mrfakename/NeuralOrca-7B-v1
5 months ago
GGUF version Please
6
#1 opened 5 months ago by
HR1777
New activity in
TheBloke/notus-7B-v1-GGUF
5 months ago
GGUF adds `<0x0A>` during tokenization due to missing `tokenizer.model`
7
#2 opened 5 months ago by
alvarobartt
New activity in
TheBloke/meditron-7B-AWQ
5 months ago
Not working on an MAC M1
2
#1 opened 5 months ago by
alex-se
New activity in
TheBloke/Yi-34B-Chat-AWQ
5 months ago
what is the difference between this model and https://huggingface.co/01-ai/Yi-34B-Chat-4bits ?
2
#1 opened 5 months ago by
hanswang73
New activity in
TheBloke/deepseek-llm-67b-chat-GGUF
5 months ago
This model requires a custom branch for GGUF
2
#3 opened 5 months ago by
Mihaiii
New activity in
TheBloke/deepseek-coder-6.7B-instruct-GPTQ
5 months ago
error while loading with exllama and AutoGPTQ
2
#2 opened 5 months ago by
anon7463435254
New activity in
TheBloke/deepseek-llm-67b-chat-GPTQ
5 months ago
Failing. Missing tokenizer.model
2
#1 opened 5 months ago by
rjmehta
New activity in
TigerResearch/tigerbot-70b-chat-v2
5 months ago
Quant pls
3
#2 opened 5 months ago by
Yhyu13
New activity in
TheBloke/Nous-Capybara-3B-v1.9-GPTQ
5 months ago
Model name with "."
1
#2 opened 5 months ago by
illorca
New activity in
TheBloke/Qwen-14B-Chat-AWQ
5 months ago
TypeError: qwen isn't supported yet.?
4
#2 opened 5 months ago by
Boffy
New activity in
berkeley-nest/Starling-LM-7B-alpha
5 months ago
Amazing model
9
#3 opened 5 months ago by
rjmehta
New activity in
TheBloke/Starling-LM-7B-alpha-GGUF
5 months ago
Tokenizer issue?
27
#1 opened 5 months ago by
sleepyjoecheated
New activity in
Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-1-7B
5 months ago
GGUF version
9
#1 opened 5 months ago by
Elfrino
New activity in
NousResearch/Nous-Capybara-7B-V1.9
5 months ago
Still showing as llama based when it should now be mistral according to card
3
#2 opened 5 months ago by
spawn99
New activity in
TheBloke/Tess-M-v1.3-GGUF
5 months ago
EOS issues
9
#1 opened 5 months ago by
dillfrescott
New activity in
TheBloke/tulu-2-7B-GPTQ
5 months ago
How to use with llama-cpp-python?
2
#1 opened 5 months ago by
lacoursj
New activity in
TheBloke/deepseek-coder-33B-instruct-GGUF
5 months ago
Models Not Loading
27
#2 opened 6 months ago by
oneCode
New activity in
TheBloke/WizardCoder-15B-1.0-GPTQ
5 months ago
Exllama not working
3
#16 opened 8 months ago by
DQ83
New activity in
TheBloke/Mistral-7B-Instruct-v0.1-GGUF
5 months ago
Can't deploy to sagemaker
3
#15 opened 5 months ago by
philgrey
New activity in
TheBloke/open-llama-7b-open-instruct-GGML
5 months ago
Update Readme to Correct 3x Typos in "VMware"
1
#1 opened 5 months ago by
ryanconley
New activity in
TheBloke/Llama-2-70B-Chat-GGUF
5 months ago
update Readme q4 to Q4
#4 opened 5 months ago by
borisalmonacid
New activity in
TheBloke/Nous-Capybara-7B-v1.9-GGUF
5 months ago
Update README.md
#1 opened 5 months ago by
LDJnr
New activity in
TheBloke/goliath-120b-GGUF
5 months ago
Model file 'goliath-120b.Q4_K_M.gguf' not found
5
#2 opened 5 months ago by
belhal
New activity in
OrionStarAI/OrionStar-Yi-34B-Chat-Llama
5 months ago
Prompt format?
2
#3 opened 5 months ago by
Yhyu13
Quantization
1
#2 opened 5 months ago by
Yhyu13
New activity in
TheBloke/Akins-3B-GGUF
5 months ago
Fix prompt template.
1
#1 opened 5 months ago by
acrastt
New activity in
TheBloke/Marx-3B-v3-GGUF
5 months ago
Fix prompt template.
#1 opened 5 months ago by
acrastt
Load more