commit 31bd996361838eff4f909c1ec852a2975c59dee0 Author: ModelHub XC Date: Sat Sep 19 01:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Pinkstack/Superthoughts-lite-1.8B-experimental-o1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..84910ed --- /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.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +superthoughts-lite.F16.gguf filter=lfs diff=lfs merge=lfs -text +superthoughts-lite.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +superthoughts-lite.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +superthoughts-lite.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..37cf661 --- /dev/null +++ b/Modelfile @@ -0,0 +1,13 @@ + +FROM /content/Pinkstack/Superthoughts-lite-1.8B-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 0.7 +PARAMETER min_p 0.95 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..2b1bc18 --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +base_model: Pinkstack/Superthoughts-lite-1.8B-experimental-o1 +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +- code +- superthoughts +- cot +- reasoning +- gguf +license: apache-2.0 +language: +- en +pipeline_tag: text-generation +new_version: Pinkstack/Superthoughts-lite-v1-GGUF +--- +![superthoughtslight.png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/2LuPB_ZPCGni3-PyCkL0-.png) + +# Information +Advanced, high-quality and lite reasoning for a tiny size that you can run locally in Q8 on your phone! 😲 + +⚠️This is an experimental version: it may not always answer your question properly or correctly. currently reasoning may not always work on long conversations, as we've trained it on single turn conversations only. +SmolLM2-1.7B-Instruct on an advanced reasoning pattern dataset (half synthetic, half written manually by us.) to create this model. Supposed to output like this: +``` +<|im_start|>user +What are you<|im_end|> +<|im_start|>assistant + +Alright, the user just asked 'What are you', meaning they want to know who I am. I think my name is Superthoughts (lite version), created by Pinkstack on January 2025. I'm ready to answer their question. + +Welcome! I'm Superthoughts (lite) created by Pinkstack in January 2025. Ready to help you with whatever you need!<|im_end|> +``` +# Which quant is right for you? +- ***Q4_k_m:*** This quant *can* be used on most devices, quality is acceptable but reasoning quality is low. +- ***Q6_k:*** This quant is right in the middle, quality is better than q4_k_m but reasoning is still more limited than Q8. +- ***Q8_0:*** **RECOMMENDED** This quant yields very high quality results, good reasoning, good answers at a fast speed, on a Snapdragon 8 Gen 2 with 16 GB's of ram, it runs on 13 tokens per minute on average, see examples below. +- ***F16:*** Maximum quality GGUF quant, not needed for most tasks, results very similar to Q8_0. + +# Examples: +all responses below generated with no system prompt, 400 maximum tokens and a temperature of 0.7 (not recommended, 0.3 - 0.5 is better): +Generated inside the android application, Pocketpal via GGUF Q8, using the model's prompt format. +1) +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/wh33o-vjxIePfPqoN3q1z.png) +2) +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/Y8optw73kTgqMnZKj3wKj.png) +3) +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/6lywy3IYEIgzPnUIJ5RvF.png) +4) +![image/png](https://cdn-uploads.huggingface.co/production/uploads/6710ba6af1279fe0dfe33afe/0K2rR9osmT20JrDvZuptV.png) + +# Uploaded model + +- **Developed by:** Pinkstack +- **License:** apache-2.0 +- **Finetuned from model :** HuggingFaceTB/SmolLM2-1.7B-Instruct + +This smollm2 model was trained with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. \ No newline at end of file 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 diff --git a/superthoughts-lite.F16.gguf b/superthoughts-lite.F16.gguf new file mode 100644 index 0000000..c8de71e --- /dev/null +++ b/superthoughts-lite.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9392ae8881a0affbf60cb770c1994badd37fc1aa2be9ef931cc937be123660a6 +size 3626063008 diff --git a/superthoughts-lite.Q4_K_M.gguf b/superthoughts-lite.Q4_K_M.gguf new file mode 100644 index 0000000..530c6cd --- /dev/null +++ b/superthoughts-lite.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5add1e94c6e9c3e4abf96e1f85d600d942e7d3135c68f5a043d4dbc3af45c4 +size 1112233120 diff --git a/superthoughts-lite.Q6_K.gguf b/superthoughts-lite.Q6_K.gguf new file mode 100644 index 0000000..5306bfa --- /dev/null +++ b/superthoughts-lite.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf07711e6f4a81b44683b80d569de70be69af653673b5b31e8211f6142fbb6f +size 1488540832 diff --git a/superthoughts-lite.Q8_0.gguf b/superthoughts-lite.Q8_0.gguf new file mode 100644 index 0000000..f18fde8 --- /dev/null +++ b/superthoughts-lite.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee515e5950fb0f36a0cf1737d920f11a5004c1b01a274b8b9633b4d3ab64d15 +size 1927369888