Hugging Face's logo
Migel Tissera's picture
TFLOPS icon 394.5 TFLOPS
175 8

Migel Tissera

migtissera
jorgetrivilin's profile picture kevinleguillou's profile picture PeterL123's profile picture
·
https://discord.gg/YDyGbuU5
migtissera

AI & ML interests

PhD in Deep Learning (2013-2016). I build intelligent systems using neural networks. Co-founder and CTO, Metaspectral. | Ethereum (ETH): 0xF9843939B3a2527Bb50B8D4bee241713081A5372

Organizations

Metaspectral's profile picture Qwen's profile picture NeuroLattice's profile picture WhiteRabbitNeo's profile picture

migtissera's activity

New activity in open-llm-leaderboard/requests about 19 hours ago

Update migtissera/Tess-v2.5-Phi-3-medium-128k-14B_eval_request_False_float16_Original.json

2
#23 opened 1 day ago by migtissera
New activity in migtissera/Tess-v2.5-Gemma-2-27B-alpha about 19 hours ago

Is this model more coherent?

1
#1 opened 1 day ago by UniversalLove333
New activity in open-llm-leaderboard/open_llm_leaderboard 1 day ago

Model failure: migtissera/Tess-v2.5.2-Qwen2-72B model

8
#799 opened 6 days ago by migtissera
New activity in open-llm-leaderboard/requests 1 day ago

Update migtissera/Llama-3-70B-Synthia-v3.5_eval_request_False_float16_Original.json
#24 opened 1 day ago by migtissera
New activity in google/gemma-2-27b 2 days ago

The base model doesn't generate coherently

2
#9 opened 2 days ago by migtissera
New activity in google/gemma-2-9b 2 days ago

Can't repro MMLU: sliding window attention implementation seems broken

3
#11 opened 5 days ago by dzhulgakov
New activity in migtissera/Tess-v2.5-Qwen2-72B-QLoRA-Adapter 11 days ago

Any plans for Tess 2.5.2 QLoRA?

3
#1 opened 12 days ago by PositiveJay
New activity in migtissera/Tess-v2.5-Phi-3-medium-128k-14B 14 days ago

eos token in gguf

9
#1 opened 14 days ago by mradermacher
New activity in bartowski/Tess-v2.5-Phi-3-medium-128k-14B-GGUF 14 days ago

EOS token is getting printed

9
#1 opened 15 days ago by migtissera
New activity in migtissera/Tess-v2.5.2-Qwen2-72B 16 days ago

Adding `safetensors` variant of this model

2
#5 opened 18 days ago by SFconvertbot
New activity in migtissera/Tess-v2.5.2-Qwen2-72B 17 days ago

Excellent model

1
#1 opened 18 days ago by FiditeNemini
New activity in migtissera/Tess-v2.5.2-Qwen2-72B 18 days ago

problem with index

2
#4 opened 18 days ago by prudant
New activity in migtissera/Tess-v2.5-Qwen2-72B 18 days ago

Missing bos_token_id in config.json

4
#2 opened 19 days ago by TouchNight
New activity in migtissera/Tess-v2.5-Qwen2-72B 20 days ago

Nice work! Do we have plan for opening source the datasets?

2
#1 opened 20 days ago by yixinsong
New activity in migtissera/Tess-v1.5 21 days ago

How Was This Created?

1
#2 opened 21 days ago by Kquant03
New activity in NousResearch/Hermes-2-Pro-Llama-3-8B 21 days ago

AGIEval and others

3
#19 opened 21 days ago by migtissera
New activity in Qwen/Qwen2-72B 26 days ago

Licence?

1
#1 opened 26 days ago by migtissera
New activity in open-llm-leaderboard/open_llm_leaderboard 28 days ago

No good way to identify number of activated parameters causes MIxtral evaluation failures

32
#680 opened 3 months ago by 0-hero
New activity in open-llm-leaderboard/open_llm_leaderboard 29 days ago

Model evaluation failed after a few days

1
#778 opened 29 days ago by migtissera
New activity in migtissera/Tess-v1.5 about 1 month ago

[bot] Conversion to Parquet
#1 opened about 1 month ago by parquet-converter
New activity in CohereForAI/aya-23-35B about 1 month ago

Cc-by-nc?

2
#4 opened about 1 month ago by migtissera
New activity in migtissera/Llama-3-8B-Synthia-v3.5 about 1 month ago

good model

1
#1 opened about 1 month ago by Utochi
New activity in liuhaotian/llava-v1.6-34b about 2 months ago

Kudos, impressive model

1
#5 opened 5 months ago by fblgit
New activity in migtissera/Tess-2.0-Mixtral-8x22B about 2 months ago

Training

1
#2 opened about 2 months ago by freegheist
New activity in migtissera/Tess-2.0-Mixtral-8x22B 3 months ago

Any chance of releasing the LoRA or QLoRA?

1
#1 opened 3 months ago by jukofyork
New activity in WhiteRabbitNeo/WRN-Chapter-1 3 months ago

`enhanced_instruction` contains the `response`

10
#2 opened 3 months ago by xzuyn
New activity in migtissera/Tess-2.0-Mixtral-8x7B-v0.2 3 months ago

Great job Migel!!!!

1
#1 opened 3 months ago by dillfrescott
New activity in databricks/dbrx-base 3 months ago

Please, authorize access for the base weight!

39
#5 opened 3 months ago by Undi95
New activity in migtissera/Tess-7B-v2.0 3 months ago

Question (Why not ChatML?)

5
#5 opened 3 months ago by mrfakename

Set sliding window to null to match Mistral-7B-Instruct-v0.2

1
#4 opened 3 months ago by veden
New activity in migtissera/Tess-2.0-Yi-34B-200K 3 months ago

Clarification: Is it Yi-34b-200k v2, or v1?

1
#1 opened 3 months ago by SabinStargem
New activity in migtissera/Tess-2.0-Mixtral-8x7B 3 months ago

what kind of dataset is Tess?

2
#1 opened 3 months ago by rombodawg
New activity in migtissera/Tess-7B-v2.0 3 months ago

Trailing space after "ASSISTANT:"

1
#3 opened 3 months ago by algorithm
New activity in migtissera/Tess-72B-v1.5b 3 months ago

Instruct-finetuning dataset

1
#6 opened 3 months ago by Andriy
New activity in migtissera/Tess-7B-v2.0 3 months ago

Dataset

2
#2 opened 3 months ago by mrfakename

Add chat template to tokenizer_config

4
#1 opened 3 months ago by Handgun1773
New activity in open-llm-leaderboard/open_llm_leaderboard 3 months ago

Model evaluation failed after 2 days

17
#622 opened 4 months ago by migtissera
New activity in WhiteRabbitNeo/WhiteRabbitNeo-33B-v1.5 3 months ago

What's the base model?

1
#3 opened 3 months ago by Dihf

What system prompt are you using on the website?

1
#2 opened 3 months ago by froggeric
New activity in WhiteRabbitNeo/WhiteRabbitNeo-13B-v1 4 months ago

Problem: Error fetching model files 401 Unauthorized.

1
#14 opened 4 months ago by hexxxus
New activity in migtissera/Tess-72B-v1.5b 4 months ago

Is it QLoRA or a full finetune?

1
#5 opened 4 months ago by Andriy

Adding Evaluation Results
#4 opened 4 months ago by leaderboard-pr-bot
New activity in WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a 4 months ago

Update README.md
#2 opened 4 months ago by medmac01
New activity in 01-ai/Yi-34B-200K 4 months ago

Weight updates?

8
#13 opened 4 months ago by brucethemoose
New activity in migtissera/Tess-M-v1.1 4 months ago

Adding Evaluation Results
#3 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-M-Creative-v1.0 4 months ago

Adding Evaluation Results
#3 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Synthia-7B-v3.0 4 months ago

Adding Evaluation Results
#3 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-M-v1.3 4 months ago

Adding Evaluation Results
#5 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-34B-v1.5b 4 months ago

Adding Evaluation Results
#2 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-XS-v1.1 4 months ago

Adding Evaluation Results
#1 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-34B-v1.4 4 months ago

Adding Evaluation Results
#1 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-10.7B-v1.5b 4 months ago

Adding Evaluation Results
#2 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-XS-Creative-v1.0 4 months ago

Adding Evaluation Results
#2 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/Tess-XS-v1-3-yarn-128K 4 months ago

Adding Evaluation Results
#1 opened 4 months ago by leaderboard-pr-bot
New activity in migtissera/SynthIA-70B-v1.5 4 months ago

Adding Evaluation Results
#2 opened 4 months ago by leaderboard-pr-bot