tanliboy (Li Tan) – Community Activity

#2 opened 30 days ago by

New activity in ContextualAI/ultrafeedback_clair_32k 22 days ago

Phi-2-Instruct-APO: aligned with Anchored Preference Optimization

9

#3 opened about 1 month ago by

rasyosef

New activity in Qwen/Qwen2.5-Math-RM-72B 24 days ago

Preference Alignment

#6 opened 26 days ago by

New activity in meta-llama/Llama-3.1-8B 27 days ago

Text Classification with LLMs

7

#30 opened 2 months ago by

dss107

New activity in NousResearch/Hermes-3-Llama-3.1-8B 27 days ago

IFEVAL drop

#16 opened 27 days ago by

New activity in Alibaba-NLP/gte-Qwen2-7B-instruct 28 days ago

bfloat16 vs. float32

#34 opened 28 days ago by

New activity in Alibaba-NLP/gte-Qwen2-1.5B-instruct 29 days ago

Qwen 2.5 1.5B retrain?

#12 opened 30 days ago by

tomaarsen

New activity in meta-llama/Llama-3.1-8B-Instruct 30 days ago

GSM8K Evaluation Result: 84.5 vs. 76.95

17

#81 opened 3 months ago by

New activity in Qwen/Qwen2-VL-7B-Instruct about 1 month ago

Finetuning script using HuggingFace (No llama-factory)

6

#32 opened about 1 month ago by

2U1

New activity in meta-llama/Llama-3.1-8B-Instruct about 1 month ago

Setting `pad_token_id` to `eos_token_id`:128001 for open-end generation.

8

#120 opened about 2 months ago by

erildo

New activity in Qwen/Qwen2-VL-7B-Instruct about 1 month ago

Have you deleted your GitHub page?

7

#10 opened about 1 month ago by

xwzy6

New activity in google/gemma-2-9b-it about 1 month ago

Sliding window vs. Global Attention

5

#41 opened about 2 months ago by

New activity in google/gemma-2-2b about 2 months ago

Gemma2-2b training uses much more momory!

#23 opened about 2 months ago by

bubbleseller

New activity in google/gemma-2b about 2 months ago

GemmaSdpaAttention vs GemmaAttention

#71 opened about 2 months ago by

canqin001

New activity in meta-llama/Llama-3.1-70B-Instruct about 2 months ago

Fix Llama 3.1 Chat Template to Properly Handle add_generation_prompt

9

#26 opened about 2 months ago by

Tostino

New activity in Qwen/Qwen2-VL-7B-Instruct about 2 months ago

🍭 Fine-tuning support for Qwen2-VL-7B-Instruct

5

#1 opened about 2 months ago by

study-hjt

New activity in google/gemma-2-9b-it about 2 months ago

Batch Inference causes degraded performance

#43 opened about 2 months ago by

New activity in google/recurrentgemma-9b-it about 2 months ago

Evaluation Result

#15 opened about 2 months ago by

New activity in meta-llama/Llama-3.1-8B-evals about 2 months ago

How is this dataset supposed to be used to evaluate the model?

#1 opened 2 months ago by

realdanielbyrne

New activity in google/gemma-2-2b-it about 2 months ago

RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

#18 opened 3 months ago by

lcahill

New activity in meta-llama/Meta-Llama-3-8B-Instruct about 2 months ago

Llama-3-Instruct with Langchain keeps talking to itself

10

#147 opened 4 months ago by

fahim9778

New activity in meta-llama/Llama-3.1-70B-Instruct about 2 months ago

Pruning

7

#24 opened 2 months ago by

dhivakarsa

New activity in google/gemma-7b about 2 months ago

Bad test results using lm-evaluation-harness

#68 opened 7 months ago by

smart-liu

New activity in meta-llama/Llama-3.1-8B-Instruct about 2 months ago

two BOS token id is right?

#97 opened 2 months ago by

hpsun

New activity in meta-llama/Llama-3.1-8B 2 months ago

Fine tuning data templates Please help

#32 opened 2 months ago by

Cagatayd

New activity in google/gemma-7b-it 2 months ago

add_special_tokens=False results in poor generation

3

#80 opened 7 months ago by

DMaksimov

New activity in Qwen/Qwen2-7B-Instruct 2 months ago

Why is "bos_token": null, in tokenizer_config.json?

6

#15 opened 2 months ago by

3Simplex

New activity in Qwen/Qwen2-Audio-7B-Instruct 2 months ago

TTS support?

3

#4 opened 2 months ago by

yukiarimo

New activity in google/gemma-2-27b 2 months ago

The base model doesn't generate coherently

#9 opened 4 months ago by

migtissera

New activity in google/gemma-2-9b 3 months ago

Fine-tuning Hyperparameters

6

#27 opened 3 months ago by

New activity in mistralai/Mistral-Nemo-Base-2407 3 months ago

Error: size mismatch for model.layers.0.self_attn.q_proj.weight:

#6 opened 3 months ago by

New activity in google/gemma-2-9b 3 months ago

dtype: float32 in base model vs. dtype: bfloat16 in the instruction fine-tuned model

#32 opened 3 months ago by

New activity in google/gemma-2-9b 4 months ago

TypeError: arange() received an invalid combination of arguments

#12 opened 4 months ago by

darrenbudiman

New activity in Qwen/Qwen2-7B 4 months ago

TypeError: 'NoneType' object cannot be interpreted as an integer

#3 opened 4 months ago by

New activity in microsoft/Phi-3-small-8k-instruct 4 months ago

Crash in Fine-tuning

#14 opened 5 months ago by

"bos_token": "<s>" vs. "<|endoftext|>"

#20 opened 4 months ago by

New activity in microsoft/Phi-3-medium-4k-instruct 5 months ago

Difference in chat templates between Phi-3-small-8k-instruct and Phi-3-medium-4k-instruct

#4 opened 5 months ago by