interstellarninja

interstellarninja's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

New activity in NousResearch/hermes-function-calling-v1 8 days ago

Possible errors in chat turn order

2

#11 opened 9 days ago by mik3ml

New activity in NousResearch/Hermes-2-Pro-Llama-3-8B about 1 month ago

Error from tokenizer config

5

#26 opened about 1 month ago by SowmithR

New activity in NousResearch/Hermes-3-Llama-3.1-8B about 1 month ago

Chat Template Issue

3

#15 opened about 1 month ago by SeanIsYoung

Chat template issue

1

#13 opened about 2 months ago by mneilly

New activity in NousResearch/Hermes-3-Llama-3.1-8B about 2 months ago

template for ollama

1

#9 opened about 2 months ago by Saxo

Chat template was missing tool_use from Hermes.

4

#2 opened 2 months ago by 3Simplex

New activity in NousResearch/Hermes-2-Pro-Llama-3-8B 3 months ago

i give 3 functions, but I still got some functions WHEN message are not related to the method description

2

#24 opened 3 months ago by xxxant

New activity in teknium/Llama-3.1-AlternateTokenizer 3 months ago

add missing solution tag

#1 opened 3 months ago by interstellarninja

New activity in NousResearch/Hermes-2-Pro-Mistral-7B 3 months ago

Add tool use template

#18 opened 4 months ago by Rocketknight1

New activity in NousResearch/Hermes-2-Theta-Llama-3-70B 3 months ago

Add example of chat templates for function calling

2

#3 opened 3 months ago by Rocketknight1

New activity in NousResearch/Hermes-2-Pro-Llama-3-8B 4 months ago

Add tool use template

25

#13 opened 5 months ago by Rocketknight1

OpenVINO IR model with int8 quantization

5

#2 opened 6 months ago by fakezeta

New activity in NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF 4 months ago

Vietnamese

1

#4 opened 4 months ago by HieuLe23x

New activity in NousResearch/Hermes-2-Pro-Mistral-7B 4 months ago

`tokenizer_config.json` has a duplicate entry for `clean_up_tokenization_spaces`

2

#17 opened 5 months ago by polarathene

New activity in NousResearch/Hermes-2-Pro-Mistral-7B 6 months ago

Datasets for function calling and JSON

5

#13 opened 7 months ago by Andriy

New activity in NousResearch/Hermes-2-Pro-Mistral-7B-GGUF 7 months ago

Context size ?

1

#5 opened 7 months ago by MaZeNsMz

New activity in NousResearch/Hermes-2-Pro-Mistral-7B 7 months ago

Update README.md

2

#3 opened 7 months ago by archit11

New activity in Qwen/Qwen1.5-0.5B 8 months ago

AttributeError: 'Qwen2TokenizerFast' object has no attribute 'eod_id'

1

#1 opened 8 months ago by interstellarninja

New activity in stabilityai/stablelm-2-zephyr-1_6b 9 months ago

ValueError: Tokenizer class Arcade100kTokenizer does not exist or is not currently imported.

3

#7 opened 9 months ago by interstellarninja

How to finetuning this model?

7

#4 opened 9 months ago by LeMoussel

RuntimeError: FlashAttention only support fp16 and bf16 data type

#5 opened 9 months ago by interstellarninja

New activity in stabilityai/stablelm-2-1_6b 9 months ago

Training with FA2 fails: AttributeError: 'FlashAttention2' object has no attribute 'attention_dropout'

8

#4 opened 9 months ago by g-ronimo

New activity in stabilityai/stablelm-2-zephyr-1_6b 9 months ago

finetuning with axolotl error with tokenizer

4

#1 opened 9 months ago by interstellarninja

New activity in NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO 9 months ago

Is their any way to implement function calling?

1

#4 opened 9 months ago by aryan1107

New activity in hivemind/gpt-j-6B-8bit over 1 year ago

Can't download the tokenizer

2

#15 opened over 1 year ago by alerio

NameError: name 'init_empty_weights' is not defined

#16 opened over 1 year ago by interstellarninja