Text Generation
PEFT
Safetensors
Chinese
qwen3
lora
dialogue-act-planning
psychological-counseling
conversational
Instructions to use UEC-InabaLab/CounselTraj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use UEC-InabaLab/CounselTraj with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "UEC-InabaLab/CounselTraj") - Notebooks
- Google Colab
- Kaggle
Use CounselTraj name for the dialogue-act trajectory planner
Browse files- README.md +6 -5
- SHA256SUMS +1 -1
README.md
CHANGED
|
@@ -12,9 +12,10 @@ tags:
|
|
| 12 |
- psychological-counseling
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# CounselTraj
|
| 16 |
|
| 17 |
-
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
|
| 57 |
-
cd CounselTraj
|
| 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
|
| 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 |
-
|
| 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
|