初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,58 @@
+*.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.dat filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-Open-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.1-8B-Open-SFT.i1-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39996663b175c5967a0ce00939f46d629c6806c405a116dd15fe906e2d9ed65b
+size 2161982176

Llama-3.1-8B-Open-SFT.i1-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7457102158b5a8c8aac9df73fd7ee28cedffdfe8c60566563549fda63d44b315
+size 2019637984

Llama-3.1-8B-Open-SFT.i1-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f4e00c0b3c83a817c01bbf6b78eb07712711fe5110d711a0c9c5187414713a
+size 2948291296

Llama-3.1-8B-Open-SFT.i1-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b6b4d98efea3d36c3fd2731693261fad76fd08f1fc0e72b827a20ab9e9103f
+size 2758499040

Llama-3.1-8B-Open-SFT.i1-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e935b0638c93ab344b206ff4a08f6d79ca78ae2a143faccaf77edfe42663b3d
+size 2605791968

Llama-3.1-8B-Open-SFT.i1-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7fcacac87021a53bf17276b5e7fb38f4a1676b49502cf338ad298e3b538dce
+size 2399222496

Llama-3.1-8B-Open-SFT.i1-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c56df880450740345e4e11b191172cbddcc9278724eca97748ea59a24a6281
+size 3784833760

Llama-3.1-8B-Open-SFT.i1-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d052d132c5509ccf3828bd21dc9b50f719db6717d85a79f4bbd92d9347ec303b
+size 3682335456

Llama-3.1-8B-Open-SFT.i1-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27ef842d941ea741f70eee0bf6ef9c9a507e0fe1bb3fa58af5a48d2da27bbf15
+size 3518757600

Llama-3.1-8B-Open-SFT.i1-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f174bc4b6309b261e5fc7c920c85bbe9dbf4dfd4511ce9f6d4e1bca6808a7ae9
+size 3274922720

Llama-3.1-8B-Open-SFT.i1-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f71d52ac25ecadbd0bd451b3b2bf818ef5428b071777bd99df53b73e058ddb
+size 4447673056

Llama-3.1-8B-Open-SFT.i1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80236163c8f50a0f34e4eaa72ccc65e3fca5deb9f5d81b7b5e6fecbbe7b79e95
+size 3179141856

Llama-3.1-8B-Open-SFT.i1-Q2_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9367679a4b9cf2acad486e6f0485596b43f49448b25fa5a537a54a3bd730d450
+size 2988825312

Llama-3.1-8B-Open-SFT.i1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78fbc1d16309d512e357039126f5ba3906badc0f65c1daf5e576345d917bf1c7
+size 4321966816

Llama-3.1-8B-Open-SFT.i1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b986873549a093c0408ae593cbd6ca482d701e74766b82afaa9b05d40d4f21d0
+size 4018928352

Llama-3.1-8B-Open-SFT.i1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac79778c0fda99a6a98bf3679d201965c260b9169693c52d9803c068d432c56e
+size 3664509664

Llama-3.1-8B-Open-SFT.i1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23e695f202ad48193731fa5b0012175006d9205d54ab97291463f2f485d5ac2
+size 4675902176

Llama-3.1-8B-Open-SFT.i1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01e4ea613e69909b40ffb369f9ff1dd4b3698193dcab9db9f03c09e7a968bff4
+size 4920744672

Llama-3.1-8B-Open-SFT.i1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3908d2645e1e5006af7f413ab0d289f505a6bd5611a5dbb27a7dfa22ea4bdd
+size 4692679392

Llama-3.1-8B-Open-SFT.i1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269c0a3917fb4e6c2a0ddffebe76cd426fa0d035f04c64be2707d7f6a67f48b8
+size 5732997856

Llama-3.1-8B-Open-SFT.i1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27cae0e6d8562ccfc6eb9a7e28b3096bb60369d12b0fb051508b42a2d7ce44d1
+size 5599304416

Llama-3.1-8B-Open-SFT.i1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce96424f5c3bb7f826589d506e31462dfaa36cdc3133c1af1669a438f0ce3cf
+size 6596016864

README.md

@@ -0,0 +1,87 @@
+---
+base_model: prithivMLmods/Llama-3.1-8B-Open-SFT
+datasets:
+- O1-OPEN/OpenO1-SFT
+language:
+- en
+library_name: transformers
+license: creativeml-openrail-m
+quantized_by: mradermacher
+tags:
+- Chain-of-Thought Activation
+- Llama3.1
+- 8B
+- CoT
+- SFT
+- text-generation-inference
+- Ollama
+- safetensors
+- Question Answering
+- Math
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags: nicoboss -->
+weighted/imatrix quants of https://huggingface.co/prithivMLmods/Llama-3.1-8B-Open-SFT
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-GGUF
+## Usage
+
+If you are unsure how to use GGUF files, refer to one of [TheBloke's
+READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
+more details, including on how to concatenate multi-part files.
+
+## Provided Quants
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Open-SFT-i1-GGUF/resolve/main/Llama-3.1-8B-Open-SFT.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
+
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+
+## FAQ / Model Request
+
+See https://huggingface.co/mradermacher/model_requests for some answers to
+questions you might have and/or if you want some other model quantized.
+
+## Thanks
+
+I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
+me use its servers and providing upgrades to my workstation to enable
+this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
+
+<!-- end -->

imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f645061445dd94dd7312a190214e118ffd3aa0ce8ee6a024f1e5bb662f92dea
+size 4988157