Hugging Face's logo
Joseph's picture
134 9 304

Joseph

Joseph717171
Erland's profile picture disibio's profile picture mondalsurojit's profile picture
·

AI & ML interests

None yet

Organizations

Hugging Face Discord Community's profile picture

Joseph717171's activity

New activity in TheDrummer/UnslopNemo-12B-v3-GGUF 5 days ago

Best prose in a model I've ever seen.

5
#5 opened 29 days ago by Dsol58
New activity in arcee-ai/SuperNova-Medius 6 days ago

Update SuperNova-Medius with a merge with Qwen/Qwen2.5-Coder-14B-Instruct + Further Training 😋

4
#12 opened 6 days ago by Joseph717171
New activity in Joseph717171/Hermes-3-Llama-3.1-8B_TIES_with_Base_Embeds_Initialized_to_Special_Instruct_Toks_dtypeF32 24 days ago

Like this experimental model merge? Leave a comment; I would love to know your thoughts and learn what you are doing with this model 😋
#1 opened 24 days ago by Joseph717171
New activity in mistralai/Ministral-8B-Instruct-2410 29 days ago

This LLM is hallucinating like crazy. Can someone verify these prompts?

28
#3 opened about 1 month ago by phil111
New activity in arcee-ai/SuperNova-Medius 29 days ago

Ideal quantization levels

2
#6 opened about 1 month ago by jadbox
New activity in prince-canuma/Ministral-8B-Instruct-2410-HF about 1 month ago

That was fast!

3
#1 opened about 1 month ago by rollercoasterX
New activity in arcee-ai/SuperNova-Medius-GGUF about 1 month ago

different Q4 models

1
#1 opened about 1 month ago by animax
New activity in rombodawg/Rombos-LLM-V2.5-Qwen-72b about 1 month ago

what is your "continuous finetuning"

7
#2 opened about 1 month ago by MaziyarPanahi
New activity in kotyKD/Llama3.1-Hermes3-SuperNovaLite-merged-with-base-8B about 1 month ago

Explain the rationale for your density values
#1 opened about 1 month ago by Joseph717171
New activity in Joseph717171/Llama-3.1-SuperNova-8B-Lite_TIES_with_Base about 2 months ago

Explain these Benchmark Results

2
#2 opened about 2 months ago by Joseph717171
New activity in arcee-ai/Llama-3.1-SuperNova-Lite about 2 months ago

Distill Llama-3.2-1B-Instruct from Llama-405B-Instruct to make SuperNova-Pico

1
#14 opened about 2 months ago by Joseph717171
New activity in HumanLLMs/README about 2 months ago

Paper? 👀

1
#1 opened about 2 months ago by Joseph717171
New activity in mistral-community/pixtral-12b-240910 2 months ago

This repo revision has at least one file that has been marked as unsafe.

2
#11 opened 2 months ago by MayensGuds
New activity in arcee-ai/Llama-3.1-SuperNova-Lite 2 months ago

Why is the tokenizer.json not the same as LLaMa-3.1-8B-Instruct

1
#6 opened 2 months ago by Joseph717171

Fixed tokenizer.json, so it is equal with LLama-3.1-8B-Instruct's tokenizer.json

1
#5 opened 2 months ago by Joseph717171

Bad at Following Following instructions

3
#3 opened 2 months ago by Daemontatox
New activity in arcee-ai/arcee-lite 2 months ago

Can you guys do distill LLaMa-3.1-70B-Instruct into LLaMa-3.1-8B-Instruct, or even better: LLaMa-3.1-405B-Instruct into LLaMa-3.1-8B-Instruct

4
#1 opened 3 months ago by Joseph717171
New activity in DontPlanToEnd/UGI-Leaderboard 2 months ago

Love the UGI Leaderboard. We should add a quantized category - as not all quantizations are equal

1
#37 opened 2 months ago by Joseph717171
New activity in bartowski/Hermes-3-Llama-3.1-8B-GGUF 2 months ago

Bartowski! Let's see how your imatrix differs from mine. 😋

5
#2 opened 2 months ago by Joseph717171
New activity in numen-tech/Meta-Llama-3.1-8B-Instruct-w4a16g128asym 2 months ago

Update private-llm-config.json: Combination of meta-llama/Meta-Llama-3.1-8B-Instruct/config.json with private-llm-config.json to update private-llm-config.json
#3 opened 2 months ago by Joseph717171