Hugging Face's logo
Raj Mehta's picture
62

Raj Mehta

rjmehta
21world's profile picture
·

AI & ML interests

None yet

Organizations

None yet

rjmehta's activity

New activity in internlm/internlm2_5-7b-chat-1m 5 days ago

Suggestion
#3 opened 17 days ago by rjmehta
New activity in google/gemma-2-27b-it 21 days ago

Exl Quants Please

1
#15 opened 21 days ago by rjmehta
New activity in deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct 27 days ago

Exl Quants please

1
#5 opened about 1 month ago by rjmehta
New activity in mlfoundations/tabula-8b about 1 month ago

How to run inference?

1
#1 opened about 1 month ago by rjmehta
New activity in LoneStriker/Phi-3-medium-4k-instruct-8.0bpw-h8-exl2 about 2 months ago

Phi-3 medium generation issue
#1 opened about 2 months ago by rjmehta
New activity in NTQAI/Nxcode-CQ-7B-orpo 2 months ago

exl quants please

2
#3 opened 2 months ago by rjmehta
New activity in abacusai/Smaug-Llama-3-70B-Instruct 2 months ago

Exl Quants pls
#5 opened 2 months ago by rjmehta
New activity in turboderp/Cat-Llama-3-70B-instruct 2 months ago

It prints only new lines.

1
#7 opened 2 months ago by rjmehta

Exl quants pls

1
#6 opened 2 months ago by rjmehta
New activity in cognitivecomputations/dolphin-2.9-llama3-70b 2 months ago

Instruct version please

1
#5 opened 2 months ago by rjmehta
New activity in MaziyarPanahi/calme-2.4-llama3-70b 3 months ago

Exl2 quants please

3
#8 opened 3 months ago by rjmehta
New activity in davidkim205/Rhea-72b-v0.5 3 months ago

Prompt format
#6 opened 3 months ago by rjmehta
New activity in gradientai/Llama-3-8B-Instruct-Gradient-1048k 3 months ago

Exl quants please
#7 opened 3 months ago by rjmehta
New activity in internlm/internlm-xcomposer2-4khd-7b 3 months ago

Multi image query
#8 opened 3 months ago by rjmehta

Multi GPU Inference
#7 opened 3 months ago by rjmehta
New activity in yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 4 months ago

GPTQ Quants

2
#11 opened 4 months ago by rjmehta
New activity in MoritzLaurer/deberta-v3-large-zeroshot-v2.0-c 4 months ago

Model Differences

1
#1 opened 4 months ago by rjmehta
New activity in liminerity/M7-7b 4 months ago

Exl2 Quants

1
#3 opened 4 months ago by rjmehta
New activity in MTSAIR/MultiVerse_70B 4 months ago

Exl2 Quantized

2
#2 opened 4 months ago by rjmehta
New activity in Nexusflow/Starling-LM-7B-beta 4 months ago

Amazing model.

3
#1 opened 4 months ago by rjmehta
New activity in berkeley-nest/Starling-LM-7B-alpha 4 months ago

Beta or V2 release?

3
#27 opened 6 months ago by rjmehta
New activity in yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 5 months ago

License?

2
#3 opened 6 months ago by rjmehta
New activity in abacusai/Smaug-72B-v0.1 5 months ago

exl2 version please

1
#4 opened 6 months ago by MarxistLeninist
New activity in gradientai/v-alpha-tross 5 months ago

GPTQ Versions
#5 opened 5 months ago by rjmehta
New activity in 01-ai/Yi-VL-34B 6 months ago

Document images

2
#7 opened 6 months ago by rjmehta
New activity in 01-ai/Yi-VL-6B 6 months ago

Document images

2
#5 opened 6 months ago by rjmehta
New activity in yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 6 months ago

Prompt format?

3
#2 opened 6 months ago by Hoioi
New activity in cognitivecomputations/laserxtral-exl2 6 months ago

CTX size.

3
#1 opened 6 months ago by altomek
New activity in TomGrc/FusionNet_7Bx2_MoE_14B 6 months ago

UNA cite

2
#5 opened 6 months ago by fblgit
New activity in Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct 7 months ago

License mismatch?

1
#4 opened 7 months ago by rjmehta
New activity in upstage/SOLAR-10.7B-Instruct-v1.0 7 months ago

Change licence type to commercial friendly

1
#16 opened 7 months ago by rjmehta
New activity in Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct 7 months ago

System prompt?

1
#3 opened 7 months ago by rjmehta
New activity in echo840/Monkey 7 months ago

Memory requirement?
#1 opened 7 months ago by rjmehta
New activity in TheBloke/deepseek-coder-33B-instruct-GPTQ 7 months ago

Model doesnt work

4
#5 opened 7 months ago by rjmehta
New activity in deepseek-ai/deepseek-coder-33b-instruct 7 months ago

GPTQ Model doesnt work

2
#16 opened 7 months ago by rjmehta
New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ 7 months ago

When can the exllamav2 be supported?

3
#4 opened 7 months ago by rjmehta
New activity in TheBloke/SUS-Chat-34B-GPTQ 7 months ago

Knowledge cutoff date?
#2 opened 7 months ago by rjmehta
New activity in TheBloke/DiscoLM-mixtral-8x7b-v2-GPTQ 8 months ago

What model is this?

2
#1 opened 8 months ago by rjmehta
New activity in DiscoResearch/DiscoLM-mixtral-8x7b-v2 8 months ago

What is this new Mistral model

3
#2 opened 8 months ago by rjmehta
New activity in berkeley-nest/Starling-LM-7B-alpha 8 months ago

Cant wait for Beta Version

5
#19 opened 8 months ago by rjmehta
New activity in DiscoResearch/DiscoLM-70b 8 months ago

Is this instruction following model?

1
#1 opened 8 months ago by rjmehta
New activity in berkeley-nest/Starling-LM-7B-alpha 8 months ago

Amazing model

9
#3 opened 8 months ago by rjmehta

Won't stop spitting training data

6
#18 opened 8 months ago by topastop

Prompt template for adding RAG Context block

5
#13 opened 8 months ago by rjmehta
New activity in deepseek-ai/deepseek-llm-67b-chat 8 months ago

tokenizer.model

1
#2 opened 8 months ago by rjmehta
New activity in TheBloke/deepseek-llm-67b-chat-GPTQ 8 months ago

Failing. Missing tokenizer.model

2
#1 opened 8 months ago by rjmehta
New activity in TheBloke/Starling-LM-7B-alpha-GPTQ 8 months ago

Thanks
#1 opened 8 months ago by rjmehta
New activity in TheBloke/platypus-yi-34b-GPTQ 8 months ago

Promp template
#1 opened 8 months ago by rjmehta
New activity in berkeley-nest/Starling-LM-7B-alpha 8 months ago

tokenizer.model

3
#5 opened 8 months ago by bartowski

Pytorch format available?

3
#7 opened 8 months ago by vmajor
New activity in TheBloke/Starling-LM-7B-alpha-AWQ 8 months ago

GPTQ please
#1 opened 8 months ago by rjmehta
New activity in cognitivecomputations/dolphin-2.2-70b 9 months ago

Incorrect answers for simple questions. 7B models are able to answer correctly.
#4 opened 9 months ago by rjmehta
New activity in SciPhi/SciPhi-Mistral-7B-32k 9 months ago

Gibberish output for 10k tokens.

16
#3 opened 9 months ago by rjmehta
New activity in TheBloke/Airoboros-L2-70b-2.2.1-GPTQ 10 months ago

The model keeps generating until max_new_token limit is reached

1
#1 opened 10 months ago by rjmehta
New activity in TheBloke/CollectiveCognition-v1.1-Mistral-7B-AWQ 10 months ago

Gibberish output when using 24k context length

3
#1 opened 10 months ago by rjmehta
New activity in lmsys/vicuna-13b-v1.5-16k 10 months ago

Gibberish output for any prompt after following prompt template and updating transformers, auto-gptq

1
#6 opened 10 months ago by rjmehta
New activity in TheBloke/vicuna-13B-v1.5-16K-GPTQ 10 months ago

The current text generation call will exceed the model's predefined maximum length (4096). Depending on the model, you may observe exceptions, performance degradation, or nothing at all.

1
#3 opened 10 months ago by rjmehta

Gibberish output for any prompt after following prompt template and updating transformers, auto-gptq

1
#4 opened 10 months ago by rjmehta
New activity in TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-GPTQ 10 months ago

ModuleNotFoundError: No module named 'transformers_modules.TheBloke.Airoboros-L2-13B-2'

4
#1 opened 10 months ago by rjmehta
New activity in TheBloke/LLongMA-2-7B-GPTQ about 1 year ago

Long awaited! Finally out!

8
#1 opened about 1 year ago by rjmehta