Hugging Face's logo
John's picture
73 2 34

John

cmp-nct
Jobaar's profile picture ijohn07's profile picture KeyboardMasher's profile picture
·
https://github.com/cmp-nct/ggllm.cpp

AI & ML interests

None yet

Organizations

StyleTTS 2 Community's profile picture

cmp-nct's activity

New activity in CausalLM/Vision-8B-MiniCPM-2_5-Uncensored-and-Detailed 2 months ago

Requesting access for quantization into llama.cpp now that OpenBMB supports it

1
#6 opened 2 months ago by cmp-nct
New activity in xtuner/llava-phi-3-mini-gguf 2 months ago

Modl showing up as Llama instead of phi3 in LMstudio

12
#1 opened 5 months ago by Tirin
New activity in CausalLM/Vision-8B-MiniCPM-2_5-Uncensored-and-Detailed 3 months ago

gguf request

1
#1 opened 4 months ago by mishaml77
New activity in internlm/internlm-xcomposer2d5-7b 3 months ago

llama.cpp support
#10 opened 3 months ago by cmp-nct
New activity in haoranxu/Llama-3-Instruct-8B-CPO 3 months ago

alma updates ?

4
#1 opened 3 months ago by cmp-nct
New activity in openbmb/MiniCPM-Llama3-V-2_5 3 months ago

gguf / llama.cpp support

2
#45 opened 3 months ago by cmp-nct

Using gguf format

7
#1 opened 4 months ago by Tomy99999
New activity in microsoft/Phi-3-vision-128k-instruct 3 months ago

[Issue] Help with the integration of phi-3-vision on llama.cpp

13
#40 opened 3 months ago by ManniX-ITA

Should Phi-3V provide support in llama.cpp?

6
#24 opened 4 months ago by haohoo
New activity in BAAI/Bunny-v1_1-Llama-3-8B-V 3 months ago

ggml/llama.cpp support ?

1
#1 opened 3 months ago by cmp-nct
New activity in openbmb/MiniCPM-Llama3-V-2_5 4 months ago

Quite exceptional - looking forward to see the fork implemented in llama.cpp - but why that fork choice ?

1
#20 opened 4 months ago by cmp-nct
New activity in xtuner/llava-llama-3-8b-transformers 4 months ago

Update generate to not ramble/repeat

1
#1 opened 4 months ago by ctranslate2-4you
New activity in xtuner/llava-llama-3-8b-v1_1-gguf 5 months ago

Update README.md

4
#1 opened 5 months ago by cmp-nct
New activity in xtuner/llava-llama-3-8b-v1_1 5 months ago

Model prone to endless repeating

4
#5 opened 5 months ago by cmp-nct

System Prompt used ?

1
#4 opened 5 months ago by cmp-nct
New activity in xtuner/llava-llama-3-8b-v1_1-hf 5 months ago

Nice model
#4 opened 5 months ago by cmp-nct
New activity in internlm/internlm-xcomposer2-vl-7b 7 months ago

Is the Vision model inside the pytorch binaries used ?
#4 opened 7 months ago by cmp-nct
New activity in cmp-nct/llava-1.6-gguf 7 months ago

LLama-cpp-python compatibility

4
#7 opened 7 months ago by enrico07

Add VLLM tag

2
#6 opened 7 months ago by osanseviero

7B Q4_k variant?

4
#5 opened 8 months ago by GJSea
New activity in liuhaotian/llava-v1.6-34b 8 months ago

GGUF version please?

3
#3 opened 8 months ago by brugoua
New activity in cmp-nct/llava-1.6-gguf 8 months ago

Do you have the llava-34b.gguf file?

7
#4 opened 8 months ago by AiCreatornator
New activity in cmp-nct/xcomposer2_gguf_for_llama.cpp_development 8 months ago

Doesn't work.

1
#1 opened 8 months ago by hellork
New activity in cmp-nct/llava-1.6-gguf 8 months ago

Not working (llama_cpp_python)

2
#3 opened 8 months ago by mjspeck

Q8?

2
#1 opened 8 months ago by FiditeNemini
New activity in liuhaotian/llava-v1.6-vicuna-13b 8 months ago

ViT size mismatch of mlp (ffn) tensors
#2 opened 8 months ago by cmp-nct
New activity in ikawrakow/validation-datasets-for-llama.cpp 8 months ago

Creating bin files

1
#1 opened 8 months ago by cmp-nct
New activity in lmsys/chatbot-arena-leaderboard 8 months ago

Re-evaluate GPT-4 ! Add a ELO-graph over time to the leaderboard

8
#19 opened 8 months ago by cmp-nct
New activity in TheBloke/WizardCoder-33B-V1.1-GGUF 8 months ago

WOW ..just wow

19
#1 opened 9 months ago by mirek190
New activity in lmsys/chatbot-arena-leaderboard 8 months ago

How does GPT-4 Turbo do so well?

10
#10 opened 9 months ago by endolith
New activity in stabilityai/stable-code-3b 8 months ago

How could I run inference with the gguf models?

6
#6 opened 8 months ago by davideuler
New activity in 01-ai/Yi-VL-34B 8 months ago

Strange tensor names - looks like a duplication error ?
#8 opened 8 months ago by cmp-nct
New activity in haoranxu/ALMA-13B-R 9 months ago

The GPT-4 comparison is a bit too early (yet?)

4
#1 opened 9 months ago by cmp-nct
New activity in OpenBuddy/openbuddy-falcon-40b-v16.1-4k 9 months ago

missing lm_head.weight tensor

2
#1 opened 9 months ago by cmp-nct
New activity in TheBloke/openchat-3.5-0106-GGUF 9 months ago

EOS token wrong

4
#1 opened 9 months ago by mljxy
New activity in Lin-Chen/ShareGPT4V-7B_Pretrained_vit-large336-l12 9 months ago

Compared to a huge vision tower
#2 opened 10 months ago by cmp-nct
New activity in Lin-Chen/ShareGPT4V-13B 9 months ago

Question on the two variants

3
#1 opened 9 months ago by cmp-nct
New activity in cmp-nct/ShareGPT4V-7B-quant-gguf 9 months ago

13B version released, can you please upload it too?

1
#1 opened 9 months ago by bababoiii
New activity in Willow123/InternLM-XComposer 10 months ago

Apply for community grant: Academic project (gpu)

5
#1 opened 12 months ago by Willow123
New activity in ise-uiuc/Magicoder-S-DS-6.7B 10 months ago

AMAZING CODING MODEL!!!

10
#1 opened 10 months ago by rombodawg
New activity in coqui/XTTS-v2 10 months ago

Emotions

7
#19 opened 10 months ago by PratikHackTR
New activity in THUDM/cogvlm-chat-hf 10 months ago

Stunningly good
#13 opened 10 months ago by cmp-nct
New activity in openchat/openchat_3.5 10 months ago

Some feedback

1
#33 opened 10 months ago by cmp-nct
New activity in jbochi/madlad400-3b-mt 10 months ago

gguf invalid and no support in llama.cpp

2
#8 opened 10 months ago by cmp-nct
New activity in LeoLM/leo-hessianai-13b-chat 10 months ago

Can you incorporate madlad400 training data ?

1
#11 opened 10 months ago by cmp-nct
New activity in google/madlad400-10b-mt 10 months ago

German translation - an upside and 2 huge problems in actually using this
#1 opened 10 months ago by cmp-nct
New activity in aiassociates/t5-small-grammar-correction-german 10 months ago

We need this but for real mistakes
#2 opened 10 months ago by cmp-nct
New activity in VAGOsolutions/SauerkrautLM-7b-HerO 10 months ago

It's not very good in grammar - big comparison on a single sentence with other models

4
#3 opened 10 months ago by cmp-nct
New activity in TheBloke/SauerkrautLM-13B-v1-GGUF 10 months ago

Wrong HF thread
#1 opened 10 months ago by cmp-nct
New activity in CausalLM/14B-DPO-alpha 10 months ago

Some feedback

2
#1 opened 10 months ago by cmp-nct
New activity in LeoLM/leo-hessianai-7b-chat-bilingual 10 months ago

Waste of energy and increased response latency from useless introductions
#2 opened 10 months ago by cmp-nct
New activity in Lin-Chen/ShareGPT4V 10 months ago

Feedback

1
#2 opened 10 months ago by cmp-nct
New activity in Lin-Chen/ShareGPT4V-7B_Pretrained_vit-large336-l12 10 months ago

Loading with ggml llava through llama.cpp (PR)

2
#1 opened 10 months ago by cmp-nct
New activity in Lin-Chen/ShareGPT4V-7B 10 months ago

You need to get better CLIP
#1 opened 10 months ago by cmp-nct
New activity in OpenBuddy/openbuddy-falcon-7b-v6-bf16 10 months ago

Please update ? Falcon is significantly better in non-english than llama-70B. Even Falcon 7B can beat it in grammar

4
#2 opened 10 months ago by cmp-nct
New activity in maddes8cht/ehartford-WizardLM-Uncensored-Falcon-40b-gguf 10 months ago

Some experience with using this model

7
#2 opened 12 months ago by Nafnlaus
New activity in tiiuae/falcon-180B about 1 year ago

Falcon 40B license vs 180B - conflict ?

3
#4 opened about 1 year ago by cmp-nct
New activity in tiiuae/falcon-40b about 1 year ago

GPU requirements

7
#68 opened over 1 year ago by GuySerk
New activity in h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 about 1 year ago

No special tokens ?

4
#5 opened about 1 year ago by cmp-nct
New activity in tiiuae/falcon-40b about 1 year ago

Finetuning Base Falcon on Unseen Language/New data (non instruct/RLHF)

2
#91 opened about 1 year ago by AshBam