From 10ee59c2cb96164210a94587b6cf03cfcadfad32 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 3 Nov 2026 05:04:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: afrideva/phi-2-psy-GGUF Source: Original Platform --- .gitattributes | 42 +++++++++++++++++++ README.md | 97 +++++++++++++++++++++++++++++++++++++++++++ phi-2-psy.fp16.gguf | 3 ++ phi-2-psy.q2_k.gguf | 3 ++ phi-2-psy.q3_k_m.gguf | 3 ++ phi-2-psy.q4_k_m.gguf | 3 ++ phi-2-psy.q5_k_m.gguf | 3 ++ phi-2-psy.q6_k.gguf | 3 ++ phi-2-psy.q8_0.gguf | 3 ++ 9 files changed, 160 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 phi-2-psy.fp16.gguf create mode 100644 phi-2-psy.q2_k.gguf create mode 100644 phi-2-psy.q3_k_m.gguf create mode 100644 phi-2-psy.q4_k_m.gguf create mode 100644 phi-2-psy.q5_k_m.gguf create mode 100644 phi-2-psy.q6_k.gguf create mode 100644 phi-2-psy.q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f08d8c8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.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 +phi-2-psy.fp16.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-psy.q2_k.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-psy.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-psy.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-psy.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-psy.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-psy.q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..068600b --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: vince62s/phi-2-psy +inference: false +license: mit +model_creator: vince62s +model_name: phi-2-psy +pipeline_tag: text-generation +quantized_by: afrideva +tags: +- merge +- mergekit +- lazymergekit +- rhysjones/phi-2-orange +- cognitivecomputations/dolphin-2_6-phi-2 +- gguf +- ggml +- quantized +- q2_k +- q3_k_m +- q4_k_m +- q5_k_m +- q6_k +- q8_0 +--- +# vince62s/phi-2-psy-GGUF + +Quantized GGUF model files for [phi-2-psy](https://huggingface.co/vince62s/phi-2-psy) from [vince62s](https://huggingface.co/vince62s) + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [phi-2-psy.fp16.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.fp16.gguf) | fp16 | 5.56 GB | +| [phi-2-psy.q2_k.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q2_k.gguf) | q2_k | 1.11 GB | +| [phi-2-psy.q3_k_m.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q3_k_m.gguf) | q3_k_m | 1.43 GB | +| [phi-2-psy.q4_k_m.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q4_k_m.gguf) | q4_k_m | 1.74 GB | +| [phi-2-psy.q5_k_m.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q5_k_m.gguf) | q5_k_m | 2.00 GB | +| [phi-2-psy.q6_k.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q6_k.gguf) | q6_k | 2.29 GB | +| [phi-2-psy.q8_0.gguf](https://huggingface.co/afrideva/phi-2-psy-GGUF/resolve/main/phi-2-psy.q8_0.gguf) | q8_0 | 2.96 GB | + + + +## Original Model Card: +# Phi-2-psy + +Phi-2-psy is a merge of the following models: +* [rhysjones/phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange) +* [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2) + +## 🏆 Evaluation + +The evaluation was performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval) on Nous suite. + +| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average| +|----------------------------------------------------------------|------:|------:|---------:|-------:|------:| +|[**phi-2-psy**](https://huggingface.co/vince62s/phi-2-psy)| **34.4**| **71.4**| **48.2**| **38.1**| **48.02**| +|[phixtral-2x2_8](https://huggingface.co/mlabonne/phixtral-2x2_8)| 34.1| 70.4| 48.8| 37.8| 47.78| +|[dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)| 33.1| 69.9| 47.4| 37.2| 46.89| +|[phi-2-orange](https://huggingface.co/rhysjones/phi-2-orange)| 33.4| 71.3| 49.9| 37.3| 47.97| +|[phi-2](https://huggingface.co/microsoft/phi-2)| 28.0| 70.8| 44.4| 35.2| 44.61| + +## 🧩 Configuration + +```yaml +slices: + - sources: + - model: rhysjones/phi-2-orange + layer_range: [0, 32] + - model: cognitivecomputations/dolphin-2_6-phi-2 + layer_range: [0, 32] +merge_method: slerp +base_model: rhysjones/phi-2-orange +parameters: + t: + - filter: self_attn + value: [0, 0.5, 0.3, 0.7, 1] + - filter: mlp + value: [1, 0.5, 0.7, 0.3, 0] + - value: 0.5 +dtype: bfloat16 +``` + +## 💻 Usage + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer +torch.set_default_device("cuda") +model = AutoModelForCausalLM.from_pretrained("vince62s/phi-2-psy", torch_dtype="auto", trust_remote_code=True) +tokenizer = AutoTokenizer.from_pretrained("vince62s/phi-2-psy", trust_remote_code=True) +inputs = tokenizer('''def print_prime(n): + """ + Print all primes between 1 and n + """''', return_tensors="pt", return_attention_mask=False) +outputs = model.generate(**inputs, max_length=200) +text = tokenizer.batch_decode(outputs)[0] +print(text) +``` \ No newline at end of file diff --git a/phi-2-psy.fp16.gguf b/phi-2-psy.fp16.gguf new file mode 100644 index 0000000..25db950 --- /dev/null +++ b/phi-2-psy.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9cf110f62d2a1d62758d98bd6235fbc5655800c377eccfcb3434a470350f2d +size 5563095616 diff --git a/phi-2-psy.q2_k.gguf b/phi-2-psy.q2_k.gguf new file mode 100644 index 0000000..a877987 --- /dev/null +++ b/phi-2-psy.q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dba61a35d6f00ccc86431d0b924a364add07212b65a03a0eb7e66c4c5001347 +size 1109719648 diff --git a/phi-2-psy.q3_k_m.gguf b/phi-2-psy.q3_k_m.gguf new file mode 100644 index 0000000..9fd549e --- /dev/null +++ b/phi-2-psy.q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78fce51c69342bcf86d699b49a596e0dd2544639be92d769d22eaf91a534f1d8 +size 1432689248 diff --git a/phi-2-psy.q4_k_m.gguf b/phi-2-psy.q4_k_m.gguf new file mode 100644 index 0000000..8d96305 --- /dev/null +++ b/phi-2-psy.q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:991a20b34c6e4fc7f039bf1a1f6413b299c58619c5a49c76f6ed933346eae1b9 +size 1737636448 diff --git a/phi-2-psy.q5_k_m.gguf b/phi-2-psy.q5_k_m.gguf new file mode 100644 index 0000000..076f117 --- /dev/null +++ b/phi-2-psy.q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb2f4e32ec05d8f551a26e8c380d77d586173e01abee65e1f2e587ba256e7f8 +size 2003057248 diff --git a/phi-2-psy.q6_k.gguf b/phi-2-psy.q6_k.gguf new file mode 100644 index 0000000..774983f --- /dev/null +++ b/phi-2-psy.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fa299888d78942231b88e1ddbb3aec069cab1e074e7e9f2c2d723e7ac3cb26 +size 2285066848 diff --git a/phi-2-psy.q8_0.gguf b/phi-2-psy.q8_0.gguf new file mode 100644 index 0000000..f762da6 --- /dev/null +++ b/phi-2-psy.q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7215bfdc5bbc6e55f40d567ab0224325a88e03c67e940b31ceb227ddaafc622 +size 2958039648