Hugging Face's logo

Spaces:
inflaton-ai
/
logical-reasoning
Build error

App Files Community
1
logical-reasoning / llama-factory /config

Commit History

7b
a36def6

inflaton commited on

qwen2.5 3/7b fine-tuned
bd723f9

inflaton commited on

updated scripts
959d8cc

dh-mc commited on

tune qwen2.5
88d67f6

dh-mc commited on

internlm2_5-7b-chat fine-tune results
e4bce5e

inflaton commited on

done fine-tuning
72043da

inflaton commited on

qwen2 72b checkpoints
9dc50d8

inflaton commited on

fix training configs
64655af

dh-mc commited on

ready for QLoRA
b87bc1a

dh-mc commited on

upload qwen2_7b_instruct p1,p2, llama3.1_8b_p2
6114e2d

HaotianHu commited on

upload qwen2_7b training results
8ca00c1

HaotianHu commited on

llama3 r4 p2 results
46c075a

inflaton commited on

ready for llama3 r4
fcc0071

dh-mc commited on

ready for internlm r3
c4a6675

dh-mc commited on

r3: hfl/llama-3-chinese-8b-instruct-v3
dab24b4

dh-mc commited on

save 3 checkpoints
f33dabc

dh-mc commited on

reduce batch size
272aed7

dh-mc commited on

llama3 en
58a3992

dh-mc commited on

llama3 r2 config
2fb55eb

dh-mc commited on

internlm p2 r2
6b4da82

inflaton commited on

Update qwen2_7b_lora_sft_4bit.yaml
6dcb228

HaotianHu commited on

llama3 results
40ad559

inflaton commited on

ready for tuning glm-4
29d9234

dh-mc commited on

llama3 epoch 6 shows promising results; adding 4 epochs
16974cb

dh-mc commited on

Delete qwen2_7b_lora_sft.yaml
641c88c

HaotianHu commited on

Create qwen2_7b_lora_sft_4bit.yaml
99be546

HaotianHu commited on

llama3 p2 epoch 1 results
4a18d7a

inflaton commited on

llama3 results
127b0e9

inflaton commited on

new llama3 base results
4203a9b

inflaton commited on

llama3 8b base model results
ad9400c

inflaton commited on

working api/test
8ef46cb

inflaton commited on

llama3 finetune config
1f778a0

dh-mc commited on

Update llama3-8b_lora_sft_bf16-p1.yaml
b2d230a

dh-mc commited on

llama3
3a63ec4

dh-mc commited on

attempted gemma2
bc0d2ff

inflaton commited on

gemma2
0d2096e

dh-mc commited on

updated logging/save/eval steps
dc1ac39

dh-mc commited on

Update qwen2_72b_lora_sft_4bit-p1.yaml
c817aef

dh-mc commited on

reduce b-->4
5f306e7

dh-mc commited on

reduce batch size to 8
103dbc8

dh-mc commited on

reduce batch size to 16
af72c0c

dh-mc commited on

fixed templates
685f9c5

dh-mc commited on

fixed dataset
25508d8

dh-mc commited on

upcast_layernorm: true for 4bit qlora
de6246f

dh-mc commited on

tune-mgtv-qwen2_72b.sh
09e6035

dh-mc commited on

sft_bf16_p2_full 4 epochs
f1e8d7b

inflaton commited on

h100 4epochs for P1
93bc929

inflaton commited on

created scripts/tune-mgtv.sh
4e8cffe

dh-mc commited on

p1 bf16 epoch 4 results
9719e3b

dh-mc commited on