Hugging Face's logo

Spaces:
inflaton-ai
/
logical-reasoning
Build error

App Files Community
1
logical-reasoning / llm_toolkit

Commit History

no padding
32463b2

dh-mc commited on

ready for final run
687f68b

dh-mc commited on

Update logical_reasoning_utils.py
0c7b7f6

dh-mc commited on

ready for qwen2.5
d5ab5d2

dh-mc commited on

mistral 5-shot
5158692

inflaton commited on

counted few-shot prompts for all models
a8683cf

dh-mc commited on

try 5-shot for open source models
d2150e8

dh-mc commited on

10-shot results ready for 7/8 B models
3db2ae5

dh-mc commited on

internlm 20b results
47d6ce1

inflaton commited on

rtx4090 0-shot
d028752

dh-mc commited on

ready for few shots eval
cf912f1

dh-mc commited on

claude 0-shot
397a2fa

inflaton commited on

o1-mini results
fd14581

inflaton commited on

openai batch
921fa92

dh-mc commited on

completed eval/analysis
468b88d

dh-mc commited on

openai zero-shot results
8b9bb19

inflaton commited on

Update eval_logical_reasoning_all_epochs.py
090acf8

dh-mc commited on

change BATCH_SIZE to 1 for qwen2-72b eval
4c31851

dh-mc commited on

open source LLM results almost done
5a8f8d2

dh-mc commited on

Update llm_utils.py
71af822

dh-mc commited on

tuning mistral cn
bbea107

inflaton commited on

ready for bf16 tuning
e656f92

dh-mc commited on

ready for QLoRA
b87bc1a

dh-mc commited on

final rank: 42
7f20241

dh-mc commited on

gemma2 training complete
3a1588f

inflaton commited on

gemma2 results
c41fec1

dh-mc commited on

fix bug for gemma2
6d673bc

inflaton commited on

fixed bug
4a18348

dh-mc commited on

Create tune_logical_reasoning.py
3e74e95

dh-mc commited on

r3 results/checkpoints
7e3048e

inflaton commited on

llama3 en result analyzed
f32ad3e

dh-mc commited on

Update llm_utils.py
1c6f4f0

dh-mc commited on

test_b resultls
7670f2e

dh-mc commited on

llama3 en
58a3992

dh-mc commited on

nv4090 results
dc7abea

dh-mc commited on

updated best results
4d1916b

dh-mc commited on

internlm2 best results
be560ea

inflaton commited on

clean up
97afc60

dh-mc commited on

l40 results with correct template: intern2
791bb54

inflaton commited on

Update llm_utils.py
2847edc

dh-mc commited on

try float32 for inference
d772d9d

dh-mc commited on

best eval LF
0b5e165

inflaton commited on

glm-4 base p1 result
6599eac

inflaton commited on

improved eval_model()
6bdefef

dh-mc commited on

M3 results
47b70ed

dh-mc commited on

eval glm-4 base model
26227a0

dh-mc commited on

add env vars: MAX_NEW_TOKENS & REPETITION_PENALTY
f754508

dh-mc commited on

Update llm_utils.py
51d9a2e

dh-mc commited on

eval merged model with NV4080
c20ebfb

inflaton commited on

eval with merged model
5f8e100

dh-mc commited on