初始化项目,由ModelHub XC社区提供模型
Model: Yano/exp-0223-027-realobs-llmagent-qwen2.5-7b Source: Original Platform
This commit is contained in:
42
README.md
Normal file
42
README.md
Normal file
@@ -0,0 +1,42 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||
datasets:
|
||||
- Yano/exp-0223-027-realobs-llmagent-alfworld-data
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- qlora
|
||||
- lora
|
||||
- merged
|
||||
- alfworld
|
||||
- agent
|
||||
- realobs-llmagent
|
||||
---
|
||||
|
||||
# exp-0223-027-realobs-llmagent-qwen2.5-7b
|
||||
|
||||
Fine-tuned from **Qwen/Qwen2.5-7B-Instruct** using **QLoRA (4-bit, Unsloth)**.
|
||||
|
||||
## Purpose
|
||||
|
||||
ALFWorld SFT combining real environment observations from experiment 016
|
||||
with LLM-renarrated agent responses (strategic THOUGHTs + ACTION-dominant format).
|
||||
|
||||
## Key Design
|
||||
- Environment responses (user): Real data from 016 (byte-exact preservation)
|
||||
- Agent responses (assistant): LLM-renarrated (strategic THOUGHT, not template)
|
||||
- Format: First turn THOUGHT+ACTION, subsequent ACTION-only, recovery THOUGHT after failures
|
||||
- Failure patterns: Naturally inherited from 016's 72% failure-containing trajectories
|
||||
|
||||
## Training Configuration
|
||||
|
||||
- Base model: Qwen/Qwen2.5-7B-Instruct
|
||||
- Method: QLoRA (4-bit), merged to 16-bit
|
||||
- Max sequence length: 2048
|
||||
- Epochs: 3
|
||||
- Learning rate: 2e-05
|
||||
- LoRA: r=64, alpha=128
|
||||
- Collator: AllAssistantTurnsCollator (all turns supervised)
|
||||
Reference in New Issue
Block a user