commit d312365e99bb97d94fca017bc59d8f9a1ca2c2e1 Author: ModelHub XC Date: Mon Aug 31 22:38:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Kquant03/NeuralTrix-7B-dpo-laser-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6547c0a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,43 @@ +*.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 +NeuralTrix-7B-DPO-Laser-ggml-model-q2_k.gguf filter=lfs diff=lfs merge=lfs -text +NeuralTrix-7B-DPO-Laser-ggml-model-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +NeuralTrix-7B-DPO-Laser-ggml-model-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralTrix-7B-DPO-Laser-ggml-model-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +NeuralTrix-7B-DPO-Laser-ggml-model-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +NeuralTrix-7B-DPO-Laser-ggml-model-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +NeuralTrix-7B-DPO-Laser-ggml-model-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +NeuralTrix-7B-DPO-Laser-ggml-model-q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q2_k.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q2_k.gguf new file mode 100644 index 0000000..82d4776 --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a07b30c6780c122e8557c60525535a04f8b20c426192786894167c02d85096 +size 2719241856 diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q3_k_m.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q3_k_m.gguf new file mode 100644 index 0000000..3bdb5e5 --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e369b82b5c0256435a2046bdf7c61cbca72887ace7086e7468bf2f3e44ca3e1c +size 3518985856 diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q4_0.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q4_0.gguf new file mode 100644 index 0000000..9df5e8c --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7a7c5fa9d3b7205b31459789f32277303c8ce18d27339bd2965b369e4b9ee3 +size 4108916352 diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q4_k_m.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q4_k_m.gguf new file mode 100644 index 0000000..859ab97 --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4266d634bd2a2ba688c6c87d41ad01636522f61698b182c479ebdfb06ce6b91 +size 4368438912 diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q5_0.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q5_0.gguf new file mode 100644 index 0000000..c826fa4 --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba76326e318799fe82f385cf4423ce4bca14608fff9ab5b7ff26a27ab68cb618 +size 4997715584 diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q5_k_m.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q5_k_m.gguf new file mode 100644 index 0000000..4d7662f --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac8c2336cfe617a69939fb949da7a2d3a84ad2cf4eba110744678df1d43c3013 +size 5131409024 diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q6_k.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q6_k.gguf new file mode 100644 index 0000000..f4ef278 --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ec9f4c7ee3acd100864bbc9fad678ea406c161244e67849d10337784df834e7 +size 5942064768 diff --git a/NeuralTrix-7B-DPO-Laser-ggml-model-q8_0.gguf b/NeuralTrix-7B-DPO-Laser-ggml-model-q8_0.gguf new file mode 100644 index 0000000..325c1b6 --- /dev/null +++ b/NeuralTrix-7B-DPO-Laser-ggml-model-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b170075ab58c47e5e70e4ffe82559849bad6072096ada30e68d5fd7f41c1b6d4 +size 7695857280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0108015 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +license: apache-2.0 +language: +- en +--- + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/IclpTHDxA6a7xc7TZ5vth.png) + +# Made using Cultrix's Model, which can be found [here](https://huggingface.co/CultriX/NeuralTrix-7B-dpo). +[Join our Discord!](https://discord.gg/ZgU79QDnE2) + +[BASE MODEL HERE](https://huggingface.co/Kquant03/NeuralTrix-7B-dpo-laser) + +NeuralTrix-7B-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): +* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B) +* [flemmingmiguel/MBX-7B-v3](https://huggingface.co/flemmingmiguel/MBX-7B-v3) +* [AiMavenAi/AiMaven-Prometheus](https://huggingface.co/AiMavenAi/AiMaven-Prometheus) + +It was then trained with DPO by Cultrix using: +* https://huggingface.co/datasets/jondurbin/truthy-dpo-v0.1 + +I performed laser_snr_math on it afterwards to see if I could improve it. + +## 🧩 Configuration + +```yaml +models: + - model: mistralai/Mistral-7B-v0.1 + # no parameters necessary for base model + - model: mlabonne/OmniBeagle-7B + parameters: + density: 0.65 + weight: 0.4 + - model: flemmingmiguel/MBX-7B-v3 + parameters: + density: 0.6 + weight: 0.35 + - model: AiMavenAi/AiMaven-Prometheus + parameters: + density: 0.6 + weight: 0.35 +merge_method: dare_ties +base_model: mistralai/Mistral-7B-v0.1 +parameters: + int8_mask: true +dtype: float16 +``` + +## 💻 Usage + +```python +!pip install -qU transformers accelerate + +from transformers import AutoTokenizer +import transformers +import torch + +model = "CultriX/NeuralTrix-7B-v1" +messages = [{"role": "user", "content": "What is a large language model?"}] + +tokenizer = AutoTokenizer.from_pretrained(model) +prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) +pipeline = transformers.pipeline( + "text-generation", + model=model, + torch_dtype=torch.float16, + device_map="auto", +) + +outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) +print(outputs[0]["generated_text"]) +``` \ No newline at end of file