初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Nemo-12B-Marlin-v2-i1-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,57 @@
+*.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
+Nemo-12B-Marlin-v2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Nemo-12B-Marlin-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text

Nemo-12B-Marlin-v2.i1-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc0ac830eb6c4af03e335f3c53dce0f5abdebbddc20dec11a12004a719ed392
+size 3221625312

Nemo-12B-Marlin-v2.i1-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99de2970cb9c4acbe7562ba92e252e5481a122d019bc6cc29963ff8675a295c0
+size 2999212512

Nemo-12B-Marlin-v2.i1-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b6b5552b8c906c94605252f96daa45e6c8af65a37c958290335eac0f3d3c76
+size 4435024352

Nemo-12B-Marlin-v2.i1-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29f3dfee3f8914c6584ed1f5ad0d651af597212605f3924de020860e45aaaa8
+size 4138473952

Nemo-12B-Marlin-v2.i1-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e609d35623bde7f8d4307e4b765460621dc9daa28221e887fd6e46866627d8d5
+size 3915078112

Nemo-12B-Marlin-v2.i1-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0039b7ed15fddd68d4df322eaa3a7def2a0929be7d92791cbe2bbcf15cdb0bb7
+size 3592313312

Nemo-12B-Marlin-v2.i1-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d77dbaafa068dabe6d858d6ca69cc50061a94ffcfab1c4522e2a250bc05f6b6
+size 5722233312

Nemo-12B-Marlin-v2.i1-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2283de091779c5ba08e6a784fde09ff4410aa07a6e35d1b5c684476750757687
+size 5562079712

Nemo-12B-Marlin-v2.i1-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f286f1efeec6e579de7153e5bebbe0c9178121bfef90f4f7e74a0584679ea7
+size 5306489312

Nemo-12B-Marlin-v2.i1-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d9cd9e81ab2b51de78892d13399dc25de38378345ede6fe6dd2d5728ff808a
+size 4945385952

Nemo-12B-Marlin-v2.i1-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca789b7a3800c66c7f075f8c75db024b740f9b2c92b6f6a4b81ea3f843cd404
+size 6742710752

Nemo-12B-Marlin-v2.i1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268ee1f29bb2f5d4b0afffdfd3b2a4bac746d36bc4aac8794ae50ca8acc819e1
+size 4791048672

Nemo-12B-Marlin-v2.i1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a30cfd2b65f017ea24f521c5b0817ca87879b4baa8614bd2392e7679b789ffa
+size 6561503712

Nemo-12B-Marlin-v2.i1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd562420ba20dbe1b2b9954d4ebec2465b155acee4b6d3cc627942588f854e66
+size 6083090912

Nemo-12B-Marlin-v2.i1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29cb87cdb09ba6abe47e03d0e619864dcc1daf87c7e3543403f4a321c79f44c
+size 5534226912

Nemo-12B-Marlin-v2.i1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1382922cdf39c61311196209f0a724a86526f33151ab58212734315f3d6fb386
+size 7094639072

Nemo-12B-Marlin-v2.i1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d53475312b0d48fc91afe42579b20952eb8565301cc2f35faf9c227ccc681a
+size 7477205472

Nemo-12B-Marlin-v2.i1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc8e572bb029eaf27f2b2d1e08e62bf45f7f1f8a4b7aa4d5d99d7a6045d1b0f
+size 7120198112

Nemo-12B-Marlin-v2.i1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0cc26259e99d059f13c9d3a52b128a7b7fef0fd0d3d13eeed014a71f90c000e
+size 8727632352

Nemo-12B-Marlin-v2.i1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43837bf103a08c9882361090f69c42729caae359ad9da10f163dec933779e908
+size 8518736352

Nemo-12B-Marlin-v2.i1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42976f46653fb63c50d3e1522d47f9c2c3a56e24a426d2a57585f983614d7a6b
+size 10056210912

README.md

@@ -0,0 +1,79 @@
+---
+base_model: UsernameJustAnother/Nemo-12B-Marlin-v2
+language:
+- en
+library_name: transformers
+license: apache-2.0
+quantized_by: mradermacher
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- mistral
+- trl
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags: nicoboss -->
+weighted/imatrix quants of https://huggingface.co/UsernameJustAnother/Nemo-12B-Marlin-v2
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-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/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Nemo-12B-Marlin-v2-i1-GGUF/resolve/main/Nemo-12B-Marlin-v2.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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:ce6a56a89b82ea8910546337b0af6475dfb47037c46d6bb759017b9040f104fc
+size 7054405