Hugging Face's logo

ShaoShuai0605
/
Harness-R1

Reinforcement Learning
Transformers
Safetensors
harness-r1
agent
Model card Files
xet
 Community
ShaoShuai0605 commited on
Commit
c1ae038
·
verified ·
1 Parent(s): efd864b

Rename checkpoint folders to harness-r1 and agent-sft-harness-r1

Browse files
Files changed (18) hide show
  1. .gitattributes +2 -0
  2. README.md +3 -3
  3. {harness-r1-e0-iter143 → agent-sft-harness-r1}/chat_template.jinja +0 -0
  4. {harness-r1-e0-iter143 → agent-sft-harness-r1}/config.json +0 -0
  5. {harness-r1-e0-iter143 → agent-sft-harness-r1}/generation_config.json +0 -0
  6. {harness-r1-e1-iter495 → agent-sft-harness-r1}/model.safetensors +0 -0
  7. {harness-r1-e0-iter143 → agent-sft-harness-r1}/preprocessor_config.json +0 -0
  8. {harness-r1-e0-iter143 → agent-sft-harness-r1}/processor_config.json +0 -0
  9. {harness-r1-e0-iter143 → agent-sft-harness-r1}/tokenizer.json +0 -0
  10. {harness-r1-e0-iter143 → agent-sft-harness-r1}/tokenizer_config.json +0 -0
  11. {harness-r1-e1-iter495 → harness-r1}/chat_template.jinja +0 -0
  12. {harness-r1-e1-iter495 → harness-r1}/config.json +0 -0
  13. {harness-r1-e1-iter495 → harness-r1}/generation_config.json +0 -0
  14. {harness-r1-e0-iter143 → harness-r1}/model.safetensors +0 -0
  15. {harness-r1-e1-iter495 → harness-r1}/preprocessor_config.json +0 -0
  16. {harness-r1-e1-iter495 → harness-r1}/processor_config.json +0 -0
  17. {harness-r1-e1-iter495 → harness-r1}/tokenizer.json +0 -0
  18. {harness-r1-e1-iter495 → harness-r1}/tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  harness-r1-e0-iter143/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  harness-r1-e1-iter495/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  harness-r1-e0-iter143/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  harness-r1-e1-iter495/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ harness-r1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ agent-sft-harness-r1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -14,14 +14,14 @@ Harness-engineer checkpoints from the paper main table.
14
 
15
  | Subfolder | Paper row |
16
  |---|---|
17
- | [`harness-r1-e0-iter143`](./harness-r1-e0-iter143) | Harness-R1 |
18
- | [`harness-r1-e1-iter495`](./harness-r1-e1-iter495) | Agent SFT + Harness-R1 |
19
 
20
  ```python
21
  from transformers import AutoModelForCausalLM, AutoTokenizer
22
 
23
  repo = "ShaoShuai0605/Harness-R1"
24
- subfolder = "harness-r1-e0-iter143" # or harness-r1-e1-iter495
25
  tok = AutoTokenizer.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
26
  model = AutoModelForCausalLM.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
27
  ```
 
14
 
15
  | Subfolder | Paper row |
16
  |---|---|
17
+ | [`harness-r1`](./harness-r1) | Harness-R1 |
18
+ | [`agent-sft-harness-r1`](./agent-sft-harness-r1) | Agent SFT + Harness-R1 |
19
 
20
  ```python
21
  from transformers import AutoModelForCausalLM, AutoTokenizer
22
 
23
  repo = "ShaoShuai0605/Harness-R1"
24
+ subfolder = "harness-r1" # or agent-sft-harness-r1
25
  tok = AutoTokenizer.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
26
  model = AutoModelForCausalLM.from_pretrained(repo, subfolder=subfolder, trust_remote_code=True)
27
  ```
{harness-r1-e0-iter143 → agent-sft-harness-r1}/chat_template.jinja RENAMED
File without changes
{harness-r1-e0-iter143 → agent-sft-harness-r1}/config.json RENAMED
File without changes
{harness-r1-e0-iter143 → agent-sft-harness-r1}/generation_config.json RENAMED
File without changes
{harness-r1-e1-iter495 → agent-sft-harness-r1}/model.safetensors RENAMED
File without changes
{harness-r1-e0-iter143 → agent-sft-harness-r1}/preprocessor_config.json RENAMED
File without changes
{harness-r1-e0-iter143 → agent-sft-harness-r1}/processor_config.json RENAMED
File without changes
{harness-r1-e0-iter143 → agent-sft-harness-r1}/tokenizer.json RENAMED
File without changes
{harness-r1-e0-iter143 → agent-sft-harness-r1}/tokenizer_config.json RENAMED
File without changes
{harness-r1-e1-iter495 → harness-r1}/chat_template.jinja RENAMED
File without changes
{harness-r1-e1-iter495 → harness-r1}/config.json RENAMED
File without changes
{harness-r1-e1-iter495 → harness-r1}/generation_config.json RENAMED
File without changes
{harness-r1-e0-iter143 → harness-r1}/model.safetensors RENAMED
File without changes
{harness-r1-e1-iter495 → harness-r1}/preprocessor_config.json RENAMED
File without changes
{harness-r1-e1-iter495 → harness-r1}/processor_config.json RENAMED
File without changes
{harness-r1-e1-iter495 → harness-r1}/tokenizer.json RENAMED
File without changes
{harness-r1-e1-iter495 → harness-r1}/tokenizer_config.json RENAMED
File without changes