vulnerable_code_qwen_coder_standard_16384_100M huggingface.co api & rufimelo vulnerable_code_qwen_coder_standard_16384_100M github AI Model

Introduction of vulnerable_code_qwen_coder_standard_16384_100M

Model Details of vulnerable_code_qwen_coder_standard_16384_100M

Sparse Autoencoders for Qwen/Qwen2.5-7B-Instruct

This repository contains 1 Sparse Autoencoder(s) (SAE) trained using SAELens .

Model Details

Property	Value
Base Model	`Qwen/Qwen2.5-7B-Instruct`
Architecture	`standard`
Input Dimension	3584
SAE Dimension	16384
Training Dataset	`TQRG/DeltaSecommits_qwen-2.5-7b-instruct_tokenized_v2_vulnerable`

Available Hook Points

Hook Point
`blocks.11.hook_resid_post`

Usage

from sae_lens import SAE

# Load an SAE for a specific hook point
sae, cfg_dict, sparsity = SAE.from_pretrained(
    release="rufimelo/vulnerable_code_qwen_coder_standard_16384_100M",
    sae_id="blocks.11.hook_resid_post"  # Choose from available hook points above
)

# Use with TransformerLens
from transformer_lens import HookedTransformer

model = HookedTransformer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")

# Get activations and encode
_, cache = model.run_with_cache("your text here")
activations = cache["blocks.11.hook_resid_post"]
features = sae.encode(activations)

Files

blocks.11.hook_resid_post/cfg.json - SAE configuration
blocks.11.hook_resid_post/sae_weights.safetensors - Model weights
blocks.11.hook_resid_post/sparsity.safetensors - Feature sparsity statistics

Training

These SAEs were trained with SAELens version 6.26.2.

Runs of rufimelo vulnerable_code_qwen_coder_standard_16384_100M on huggingface.co

Total runs

24-hour runs

3-day runs

7-day runs

30-day runs

More Information About vulnerable_code_qwen_coder_standard_16384_100M huggingface.co Model

vulnerable_code_qwen_coder_standard_16384_100M huggingface.co

vulnerable_code_qwen_coder_standard_16384_100M huggingface.co is an AI model on huggingface.co that provides vulnerable_code_qwen_coder_standard_16384_100M's model effect (), which can be used instantly with this rufimelo vulnerable_code_qwen_coder_standard_16384_100M model. huggingface.co supports a free trial of the vulnerable_code_qwen_coder_standard_16384_100M model, and also provides paid use of the vulnerable_code_qwen_coder_standard_16384_100M. Support call vulnerable_code_qwen_coder_standard_16384_100M model through api, including Node.js, Python, http.

vulnerable_code_qwen_coder_standard_16384_100M huggingface.co Url

https://huggingface.co/rufimelo/vulnerable_code_qwen_coder_standard_16384_100M

rufimelo vulnerable_code_qwen_coder_standard_16384_100M online free

vulnerable_code_qwen_coder_standard_16384_100M huggingface.co is an online trial and call api platform, which integrates vulnerable_code_qwen_coder_standard_16384_100M's modeling effects, including api services, and provides a free online trial of vulnerable_code_qwen_coder_standard_16384_100M, you can try vulnerable_code_qwen_coder_standard_16384_100M online for free by clicking the link below.

rufimelo vulnerable_code_qwen_coder_standard_16384_100M online free url in huggingface.co:

https://huggingface.co/rufimelo/vulnerable_code_qwen_coder_standard_16384_100M

vulnerable_code_qwen_coder_standard_16384_100M install

vulnerable_code_qwen_coder_standard_16384_100M is an open source model from GitHub that offers a free installation service, and any user can find vulnerable_code_qwen_coder_standard_16384_100M on GitHub to install. At the same time, huggingface.co provides the effect of vulnerable_code_qwen_coder_standard_16384_100M install, users can directly use vulnerable_code_qwen_coder_standard_16384_100M installed effect in huggingface.co for debugging and trial. It also supports api for free installation.