Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
qwen3_vl
vision-language
visual-token-pruning
visionzip
scopd
Instructions to use enmingzhangzz/SCOPD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use enmingzhangzz/SCOPD with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="enmingzhangzz/SCOPD")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("enmingzhangzz/SCOPD", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use enmingzhangzz/SCOPD with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "enmingzhangzz/SCOPD" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "enmingzhangzz/SCOPD", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/enmingzhangzz/SCOPD
- SGLang
How to use enmingzhangzz/SCOPD with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "enmingzhangzz/SCOPD" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "enmingzhangzz/SCOPD", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "enmingzhangzz/SCOPD" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "enmingzhangzz/SCOPD", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use enmingzhangzz/SCOPD with Docker Model Runner:
docker model run hf.co/enmingzhangzz/SCOPD
Publish scopd-plus-reverse-kl
Browse files
models/scopd-plus-reverse-kl/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# SCOPD+ Reverse KL
|
| 2 |
+
|
| 3 |
+
LoRA adapter for Qwen2.5-VL-7B-Instruct.
|
| 4 |
+
|
| 5 |
+
Objective: reverse KL: KL(student || teacher).
|
| 6 |
+
|
| 7 |
+
Selection: top 10% budget-JSD response tokens.
|
| 8 |
+
|
| 9 |
+
See the [collection model card](../../README.md) for download and evaluation.
|
models/scopd-plus-reverse-kl/adapter_config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": "layers",
|
| 14 |
+
"layers_to_transform": [
|
| 15 |
+
0,
|
| 16 |
+
1,
|
| 17 |
+
2,
|
| 18 |
+
3,
|
| 19 |
+
4,
|
| 20 |
+
5,
|
| 21 |
+
6,
|
| 22 |
+
7,
|
| 23 |
+
8,
|
| 24 |
+
9,
|
| 25 |
+
10,
|
| 26 |
+
11,
|
| 27 |
+
12,
|
| 28 |
+
13,
|
| 29 |
+
14,
|
| 30 |
+
15,
|
| 31 |
+
16,
|
| 32 |
+
17,
|
| 33 |
+
18,
|
| 34 |
+
19,
|
| 35 |
+
20,
|
| 36 |
+
21,
|
| 37 |
+
22,
|
| 38 |
+
23,
|
| 39 |
+
24,
|
| 40 |
+
25,
|
| 41 |
+
26,
|
| 42 |
+
27
|
| 43 |
+
],
|
| 44 |
+
"loftq_config": {},
|
| 45 |
+
"lora_alpha": 32,
|
| 46 |
+
"lora_bias": false,
|
| 47 |
+
"lora_dropout": 0.0,
|
| 48 |
+
"megatron_config": null,
|
| 49 |
+
"megatron_core": "megatron.core",
|
| 50 |
+
"modules_to_save": null,
|
| 51 |
+
"peft_type": "LORA",
|
| 52 |
+
"qalora_group_size": 16,
|
| 53 |
+
"r": 16,
|
| 54 |
+
"rank_pattern": {},
|
| 55 |
+
"revision": "cc594898137f460bfe9f0759e9844b3ce807cfb5",
|
| 56 |
+
"target_modules": [
|
| 57 |
+
"v_proj",
|
| 58 |
+
"up_proj",
|
| 59 |
+
"o_proj",
|
| 60 |
+
"down_proj",
|
| 61 |
+
"gate_proj",
|
| 62 |
+
"k_proj",
|
| 63 |
+
"q_proj"
|
| 64 |
+
],
|
| 65 |
+
"target_parameters": null,
|
| 66 |
+
"task_type": "CAUSAL_LM",
|
| 67 |
+
"trainable_token_indices": null,
|
| 68 |
+
"use_dora": false,
|
| 69 |
+
"use_qalora": false,
|
| 70 |
+
"use_rslora": false
|
| 71 |
+
}
|
models/scopd-plus-reverse-kl/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a7c4004928c80f85a66d216c6d17b17005fe89740da946d7597225775b00baa
|
| 3 |
+
size 161539072
|
models/scopd-plus-reverse-kl/provenance.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"id": "scopd-plus-reverse-kl",
|
| 3 |
+
"label": "SCOPD+ Reverse KL",
|
| 4 |
+
"objective": "reverse KL: KL(student || teacher)",
|
| 5 |
+
"selection": "top 10% budget-JSD response tokens",
|
| 6 |
+
"selection_fraction": 0.1,
|
| 7 |
+
"budget_delta": 0.01,
|
| 8 |
+
"adapter_sha256": "1a7c4004928c80f85a66d216c6d17b17005fe89740da946d7597225775b00baa",
|
| 9 |
+
"source_revision": "dc2490eaf9b8b35b7e5553080dd985d0ab6a86a3",
|
| 10 |
+
"base_model": "Qwen/Qwen2.5-VL-7B-Instruct",
|
| 11 |
+
"base_revision": "cc594898137f460bfe9f0759e9844b3ce807cfb5",
|
| 12 |
+
"merged": false,
|
| 13 |
+
"format": "peft_lora",
|
| 14 |
+
"dtype": "float32",
|
| 15 |
+
"inference_dtype": "bfloat16",
|
| 16 |
+
"questions_processed": 10240,
|
| 17 |
+
"path": "models/scopd-plus-reverse-kl",
|
| 18 |
+
"tensor_count": 392,
|
| 19 |
+
"parameter_count": 40370176,
|
| 20 |
+
"weight_bytes": 161480704,
|
| 21 |
+
"lora_rank": 16,
|
| 22 |
+
"lora_alpha": 32,
|
| 23 |
+
"lora_dropout": 0.0
|
| 24 |
+
}
|