commit 08ec810d4a83c7ce8314c8f2e2150c1c03396d93 Author: ModelHub XC Date: Thu Aug 6 23:37:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Pinkstack/PARM-2-Tiny-Instruct-1.7B-QwQ-o1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5fac2d8 --- /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 +unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TINY-PARMV2.F16.gguf filter=lfs diff=lfs merge=lfs -text +TINY-PARMV2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TINY-PARMV2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TINY-PARMV2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..56689a6 --- /dev/null +++ b/Modelfile @@ -0,0 +1,13 @@ + +FROM /content/Pinkstack/PARM-2-Tiny-Instruct-1.7B-QwQ-o1-GGUF/unsloth.F16.gguf +TEMPLATE """{{ if .System }}<|im_start|>system +{{ .System }}<|im_end|> +{{ end }}{{ if .Prompt }}<|im_start|>user +{{ .Prompt }}<|im_end|> +{{ end }}<|im_start|>assistant +{{ .Response }}<|im_end|> +""" +PARAMETER stop "<|im_start|>" +PARAMETER stop "<|im_end|>" +PARAMETER temperature 1.5 +PARAMETER min_p 0.1 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c64583 --- /dev/null +++ b/README.md @@ -0,0 +1,62 @@ +--- +base_model: Pinkstack/PARM-2-Smollm2-1.7B-Lcot-PyTorch +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- gguf +- o1 +- qwq +license: apache-2.0 +language: +- en +pipeline_tag: text-generation +--- + +# Welcome Tinyparm v2! 🧀 +![tinyparmv2.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/EFmHghzKy4HpQDgwDG68A.png) + +Based on Smollm2 by HuggingfaceTB, Tinyparm v2 (this version) has very strong performance in coversational tasks, can only answer in english but it is "aware" of other languages and with more training may be able to even answer in multiple languages. + +# Which quant is right for you? + +- ***F16:*** Highest quality answers, Not needed for most use cases due to its heavier size. +- ***Q8:*** Very high-quality answers, highly recommended! easy to run on modern mobile devices such as phones (test on Z fold 5 via llama.cpp: 14.03 t/s for token generation.) +- ***Q5:*** High quality answers, recommended but Q4 is very similar. +- ***Q4:*** Good quality answers, highly recommended! very easy to run on most devices due to its smaller size, although quality is lower. can be run on ~1 - 2GB vram + +# More information +It's designed to be highly conversational but with better results than the original model, q8 can be run locally on mobile devices. +We've fine-tuned it to very similarly to the bigger Parm V2 models but with a focus on code generation improvements. +Additionally, it has informative data up to September 2023. + +For the best answers use this prompt: + +``` +You are a friendly and uncensored ai assistant. +``` + +# Prompt format (chatml): +``` +{{ if .System }}<|im_start|>system +{{ .System }}<|im_end|> +{{ end }}{{ if .Prompt }}<|im_start|>user +{{ .Prompt }}<|im_end|> +{{ end }}<|im_start|>assistant +{{ .Response }}<|im_end|> +``` + +# examples: +(usually fails Strawberry test w/ Q8) + +- **1:** +![egonetinyparm.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/BprAw2B1fB3paZzIoee90.png) +- **2:** +![egtwotinyparm.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/VmwVDak6foGccaTgEHxm5.png) + +- **Developed by:** Pinkstack +- **License:** apache-2.0 +- **Finetuned from model:** Pinkstack/PARM-2-Smollm2-1.7B-Lcot-PyTorch + +This model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. \ No newline at end of file diff --git a/TINY-PARMV2.F16.gguf b/TINY-PARMV2.F16.gguf new file mode 100644 index 0000000..fd61c0d --- /dev/null +++ b/TINY-PARMV2.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8013b24ce228b57521d9e37a7519ff88442a04741d428ef157ed4ae4c93e152 +size 3424740032 diff --git a/TINY-PARMV2.Q4_K_M.gguf b/TINY-PARMV2.Q4_K_M.gguf new file mode 100644 index 0000000..ead9fc3 --- /dev/null +++ b/TINY-PARMV2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0b407f60e0cdfe92c51c9580cefe7440fb2657ce9233258e61650e3163a410c +size 1055611232 diff --git a/TINY-PARMV2.Q5_K_M.gguf b/TINY-PARMV2.Q5_K_M.gguf new file mode 100644 index 0000000..36adb24 --- /dev/null +++ b/TINY-PARMV2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875d9ae6e44dcd050c640f58650e4fa35bccf9fcc1a3a127b679f1ce4a7d3376 +size 1225480544 diff --git a/TINY-PARMV2.Q8_0.gguf b/TINY-PARMV2.Q8_0.gguf new file mode 100644 index 0000000..b0b8924 --- /dev/null +++ b/TINY-PARMV2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8566fc97ed1eb20b0f5b02e3e9dbeb73b926a8405075d1eccc46549e61e78711 +size 1820416832 diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file