ZhiyangQi97 commited on
Commit
70edfd4
·
verified ·
1 Parent(s): 0731207

Use CounselTraj name for the dialogue-act trajectory planner

Browse files
Files changed (2) hide show
  1. README.md +6 -5
  2. SHA256SUMS +1 -1
README.md CHANGED
@@ -12,9 +12,10 @@ tags:
12
  - psychological-counseling
13
  ---
14
 
15
- # CounselTraj-DA
16
 
17
- CounselTraj-DA is the dialogue-act trajectory planning model used in CounselTraj.
 
18
  Given a brief counseling dialogue, the planner produces an ordered trajectory
19
  of role-tagged acts such as `counselor:[OpenQuestion]` and
20
  `client:[SelfDisclosure]` for subsequent dialogue synthesis.
@@ -53,8 +54,8 @@ Authenticate with a Hugging Face account that has access to this private model:
53
  ```bash
54
  pip install huggingface_hub
55
  hf auth login
56
- python -c 'from huggingface_hub import snapshot_download; snapshot_download("UEC-InabaLab/CounselTraj-DA", local_dir="CounselTraj-DA")'
57
- cd CounselTraj-DA
58
  pip install -r requirements.txt
59
  python plan_trajectory.py --input-file examples/input.jsonl --limit 1
60
  ```
@@ -88,7 +89,7 @@ import torch
88
  from peft import PeftModel
89
  from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
90
 
91
- repo_id = "UEC-InabaLab/CounselTraj-DA"
92
  tokenizer = AutoTokenizer.from_pretrained(repo_id)
93
  base = AutoModelForCausalLM.from_pretrained(
94
  "Qwen/Qwen3-8B",
 
12
  - psychological-counseling
13
  ---
14
 
15
+ # CounselTraj
16
 
17
+ CounselTraj is a dialogue-act trajectory planner for synthesizing process-aware
18
+ psychological counseling dialogues.
19
  Given a brief counseling dialogue, the planner produces an ordered trajectory
20
  of role-tagged acts such as `counselor:[OpenQuestion]` and
21
  `client:[SelfDisclosure]` for subsequent dialogue synthesis.
 
54
  ```bash
55
  pip install huggingface_hub
56
  hf auth login
57
+ python -c 'from huggingface_hub import snapshot_download; snapshot_download("UEC-InabaLab/CounselTraj", local_dir="CounselTraj")'
58
+ cd CounselTraj
59
  pip install -r requirements.txt
60
  python plan_trajectory.py --input-file examples/input.jsonl --limit 1
61
  ```
 
89
  from peft import PeftModel
90
  from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
91
 
92
+ repo_id = "UEC-InabaLab/CounselTraj"
93
  tokenizer = AutoTokenizer.from_pretrained(repo_id)
94
  base = AutoModelForCausalLM.from_pretrained(
95
  "Qwen/Qwen3-8B",
SHA256SUMS CHANGED
@@ -1,4 +1,4 @@
1
- cd82027e031fc96ad661cbc24fc0e3aefd88f636a35f1eaf6c2d5a92ba4385b1 README.md
2
  d14558619c5941e26716db37de14547c202bffe9d0bffc2492bd9ea788bad2a3 adapter_config.json
3
  f9cf6a1654d91c341678d2464098bc26c27bc58404cd57bc0a6f227d50bb6631 adapter_model.safetensors
4
  c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680 added_tokens.json
 
1
+ bd2e0cda1f215a9a94fa33ca813368561c3c86b971c8a3867a6f40ee0ef2db08 README.md
2
  d14558619c5941e26716db37de14547c202bffe9d0bffc2492bd9ea788bad2a3 adapter_config.json
3
  f9cf6a1654d91c341678d2464098bc26c27bc58404cd57bc0a6f227d50bb6631 adapter_model.safetensors
4
  c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680 added_tokens.json