commit f26feea512b28ae40ac66d1a85cf7ee1fc5bb30c Author: ModelHub XC Date: Sat Apr 11 16:20:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: noctrex/OpenThinker-Agent-v1-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4f0163a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,44 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-BF16.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-F16.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenThinker-Agent-v1-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenThinker-Agent-v1-abliterated-BF16.gguf b/OpenThinker-Agent-v1-abliterated-BF16.gguf new file mode 100644 index 0000000..3874bf0 --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae546e9254c03acbf6573da2141e9165380f59347a103b6aab04bf1b4c70718 +size 16388043616 diff --git a/OpenThinker-Agent-v1-abliterated-F16.gguf b/OpenThinker-Agent-v1-abliterated-F16.gguf new file mode 100644 index 0000000..b9f5ce9 --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae2e8c57d624a49b1fe153e863c6f60f80b5f143e821b644b3aa23b46e604d3 +size 16388043616 diff --git a/OpenThinker-Agent-v1-abliterated-IQ4_NL.gguf b/OpenThinker-Agent-v1-abliterated-IQ4_NL.gguf new file mode 100644 index 0000000..2a5c285 --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7995f697c4de833fc0f53093d486136251bfd6e4f199bcc15705b177ecceffb +size 4793623616 diff --git a/OpenThinker-Agent-v1-abliterated-IQ4_XS.gguf b/OpenThinker-Agent-v1-abliterated-IQ4_XS.gguf new file mode 100644 index 0000000..1b8f975 --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba287eea43231a147b1c02744c6d6f68b99d0319953f736b1c02f8035f287642 +size 4561839168 diff --git a/OpenThinker-Agent-v1-abliterated-Q4_K_M.gguf b/OpenThinker-Agent-v1-abliterated-Q4_K_M.gguf new file mode 100644 index 0000000..cb916b2 --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5f87a4ab080690e0867c47ac5cf8170fcf7e9d33dc58cb37168749f47c5b3f4 +size 5027783744 diff --git a/OpenThinker-Agent-v1-abliterated-Q5_K_M.gguf b/OpenThinker-Agent-v1-abliterated-Q5_K_M.gguf new file mode 100644 index 0000000..f64f907 --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f9d94fe6c7e28fd8cb82b08df93892846193fce476744389474632ad7dc19c +size 5851112512 diff --git a/OpenThinker-Agent-v1-abliterated-Q6_K.gguf b/OpenThinker-Agent-v1-abliterated-Q6_K.gguf new file mode 100644 index 0000000..4f840be --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:913dcbea2e7b00995343323f0619618473f2ef21511f4ff9076346833a0dce0e +size 6725899328 diff --git a/OpenThinker-Agent-v1-abliterated-Q8_0.gguf b/OpenThinker-Agent-v1-abliterated-Q8_0.gguf new file mode 100644 index 0000000..b8741d3 --- /dev/null +++ b/OpenThinker-Agent-v1-abliterated-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0431240c7be91b2c237216cf3a6c5216b8e1401bcece2f21e2380f5ff23e387e +size 8709518176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a0bdbc --- /dev/null +++ b/README.md @@ -0,0 +1,141 @@ +--- +pipeline_tag: text-generation +tags: +- uncensored +- abliterated +base_model: +- open-thoughts/OpenThinker-Agent-v1 +--- +This is an abliterated version of [OpenThinker-Agent-v1](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1), made using [Heretic](https://github.com/p-e-w/heretic) v1.0.1 + +The quantizations were created using an imatrix merged from [combined\_en\_medium](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_en_medium.parquet) and [harmful.txt](https://github.com/Sumandora/remove-refusals-with-transformers) to leverage the abliterated nature of the model. + +## Performance + +| Metric | This model | [Original model](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1) | +| :----- | :--------: | :---------------------------: | +| **Refusals** | 3/100 | 99/100 | + +## Analysis against the original model: +Detailed Analysis: +- Total Tensors: 399 +- Tensors with Diffs: 202 (50.6%) +- Average % Diff: 6.35% +- Median % Diff: 0.00% +- Min/Max % Diff: 0.00% / 46.22% +- Std Dev % Diff: 15.56% +- Skewness % Diff: 2.04 +- Avg L2 Norm: 125405.56 +- Tensors with >5% diff: 57 +- Top differences: + blk.35.attn_output.weight ((4096, 8192), L2: 668013.65): 46.22% + blk.34.ffn_down.weight ((4096, 24576), L2: 1155843.86): 46.07% + blk.18.attn_output.weight ((4096, 8192), L2: 667142.18): 46.00% + blk.16.ffn_down.weight ((4096, 24576), L2: 1154713.83): 45.95% + blk.24.attn_output.weight ((4096, 8192), L2: 666019.48): 45.66% + + +File Comparison: +File 1: Avg Abs Value = 77.9178, Deviation Score = 0.0991 +File 2: Avg Abs Value = 77.9111, Deviation Score = 0.0991 +Positive Diffs (File 1 > File 2): 143, Negative Diffs (File 2 > File 1): 59 + + + +![Tensor Difference Distribution](tensor_difference_distribution.png) + +![Tensor Charts](tensor_charts.png) + +## BibTeX entry and citation info +```bibtex +@misc{heretic, + author = {Weidmann, Philipp Emanuel}, + title = {Heretic: Fully automatic censorship removal for language models}, + year = {2025}, + publisher = {GitHub}, + journal = {GitHub repository}, + howpublished = {\url{https://github.com/p-e-w/heretic}} +} +``` + +# Original model card: + + +

+ +

+ +

+Project | +SFT dataset | +RL dataset | +SFT model | +RL model +

+ + +# OpenThinker-Agent-v1 + +**OpenThoughts-Agent** is an open-source effort to curate the best datasets for training agents. Our first release includes [datasets](https://huggingface.co/collections/open-thoughts/openthinker-agent), [models](https://huggingface.co/collections/open-thoughts/openthinker-agent) and our [research codebase](https://github.com/open-thoughts/OpenThoughts-Agent). + +[OpenThinker-Agent-v1](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1) is a model trained for agentic tasks such as **Terminal-Bench 2.0** and **SWE-Bench**. + +The [OpenThinker-Agent-v1](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1) model is post-trained from [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B). +It is SFT-ed on the [OpenThoughts-Agent-v1-SFT](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT) dataset, then RL-ed on the [OpenThoughts-Agent-v1-RL](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-RL) dataset. + +This model is the final model after both SFT and RL. For the model after the SFT stage only, see [OpenThinker-Agent-v1-SFT](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1-SFT). + +- **Homepage:** https://www.openthoughts.ai/blog/agent +- **Repository:** https://github.com/open-thoughts/OpenThoughts-Agent + + +# OpenThinker-Agent-v1 Model Performance + +Our [OpenThinker-Agent-v1](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-RL) model is the state-of-the-art model at its scale on agent benchmarks. + +| Model | Harness | Terminal-Bench 2.0 | SWE-Bench Verified | OpenThoughts-TB-Dev | +| ----------------------------------------------------------------------------------------------- | ------- | ------------------ | --------- | ------------------- | +| [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) | Terminus-2 | 0.0 | 0.7 | 5.7 | +| **[OpenThinker-Agent-v1](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1)** | Terminus-2 | 4.9 | 15.7 | 17.3 | +| [Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) | Terminus-2 | 1.9 | 5.7 | 10.2 | +| [Qwen/Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) | OpenHands | 10.1 | 49.2 | 24.5 | + + +# Data + +We built [OpenThinker-Agent-v1](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1) in two stages: **supervised fine-tuning**, followed by **reinforcement learning**. +Each stage required its own data pipeline – RL tasks (instructions, environments, and verifiers) and SFT traces from strong teacher agents completing tasks. + +[OpenThoughts-Agent-v1-SFT](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT) is an SFT trace dataset containing approximately **15,200 traces** drawn from two different data sources we curate: +- **nl2bash**: Simple synthetically generated tasks where the agent has to format shell commands effectively +- **InferredBugs**: A set of bugs in C# and Java collected by Microsoft that we turned into tasks + +[OpenThoughts-Agent-v1-RL](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-RL) is an RL dataset containing ~720 tasks drawn from the **nl2bash verified** dataset. + +To stabilize training, we built a three-stage filtration pipeline that prunes tasks before they ever hit the learner: + +1. Bad verifiers filter: drop tasks with flaky or excessively slow verifiers. +2. Environment stability: remove tasks whose containers take too long to build or tear down. +Optional difficulty filter: discard tasks that even a strong model (GPT-5 Codex) cannot solve in a single pass. + + +# Links +- 🌐 [OpenThoughts-Agent project page](https://www.openthoughts.ai/blog/agent) +- 💻 [OpenThoughts-Agent GitHub repository](https://github.com/open-thoughts/OpenThoughts-Agent) +- 🧠 [OpenThoughts-Agent-v1-SFT dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-SFT) +- 🧠 [OpenThoughts-Agent-v1-RL dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts-Agent-v1-RL) +- 🧠 [OpenThoughts-TB-dev dataset](https://huggingface.co/datasets/open-thoughts/OpenThoughts-TB-dev) +- 🤖 [OpenThinker-Agent-v1 model](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1) +- 🤖 [OpenThinker-Agent-v1-SFT model](https://huggingface.co/open-thoughts/OpenThinker-Agent-v1-SFT) + + +# Citation +``` +@misc{openthoughts-agent, + author = {Team, OpenThoughts-Agent}, + month = Dec, + title = {{OpenThoughts-Agent}}, + howpublished = {https://open-thoughts.ai/agent}, + year = {2025} +} +``` diff --git a/imatrix.gguf b/imatrix.gguf new file mode 100644 index 0000000..ef6eebb --- /dev/null +++ b/imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2288a05955cd1b50e74a22d0d4aed1877c8d5f248ac132c0b123978520df7a3 +size 5347200 diff --git a/tensor_charts.png b/tensor_charts.png new file mode 100644 index 0000000..7a05c19 Binary files /dev/null and b/tensor_charts.png differ diff --git a/tensor_difference_distribution.png b/tensor_difference_distribution.png new file mode 100644 index 0000000..eedba28 Binary files /dev/null and b/tensor_difference_distribution.png differ