初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,50 @@
+*.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
+Llama-3.1-8B-instruct-bilibili.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.f16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3.1-8B-instruct-bilibili.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3.1-8B-instruct-bilibili.IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8a65aad14fd75d3f8ff43c573f1700d6036b6d1b673fdd81808a85450c3b27
+size 3784828800

Llama-3.1-8B-instruct-bilibili.IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0fdca7039257b10bb1dcdccc7303fcdc8f066f6dac088a8a3b571f5f0eab57d
+size 3682330496

Llama-3.1-8B-instruct-bilibili.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f15b4d35c80105f6e1a0d94a910b988bd116af230700d124c023d204a12850
+size 3518752640

Llama-3.1-8B-instruct-bilibili.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f45f94173239497fb3b4854e844598ab8c79ff86a01e9202cd13269fb17a5cb3
+size 4484368256

Llama-3.1-8B-instruct-bilibili.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0c39a71bc8651f775fd777ad45ac61f89d05fdf500808cd8c5c968da4fd735
+size 3179136896

Llama-3.1-8B-instruct-bilibili.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2061972b2d286f5cbed5f5cc0d594d2553c9054bbaa4cc3cceb604ef973d4cd6
+size 4321961856

Llama-3.1-8B-instruct-bilibili.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1197b47b8616c66b1c63d106de18acd85026ab6df18cc1a01a5e4d8c4d213a8
+size 4018923392

Llama-3.1-8B-instruct-bilibili.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2040e9eca8e89fdeb028ce71afdf51dbc5d582621892ff4bbea5829e00fffc53
+size 3664504704

Llama-3.1-8B-instruct-bilibili.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf916967c02c0ecbeba1d97d7d1ff6a63aeea2ceeb951fe48ba2636e9e63637
+size 4920739712

Llama-3.1-8B-instruct-bilibili.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220f53b4d3b60e6ec2a82ba6758a33d0b3681967fbb66b5baf33744fa86f61cb
+size 4692674432

Llama-3.1-8B-instruct-bilibili.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8704f59051761ff40d5977a1ed71e9051fb4c5d0c4e13e98e4a60c1360ab4f3
+size 5732992896

Llama-3.1-8B-instruct-bilibili.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4404eb5e7e1c1dc73121c4f061a7c74be2c6e2196c11ac48592f519e5bd7bea4
+size 5599299456

Llama-3.1-8B-instruct-bilibili.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:731fa4231a3cdae920003aa9c084522833f19a9adc02e3b729e052903dddb9d4
+size 6596011904

Llama-3.1-8B-instruct-bilibili.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1762f9554e82483a672d0cf6d897f3bf770470d69810906384dc2fbe567c93
+size 8540776320

Llama-3.1-8B-instruct-bilibili.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dea51453f635f2801b2003280ae19ccce51fe354af1cbed8230c47bbdfb067f
+size 16068896640

README.md

@@ -0,0 +1,74 @@
+---
+base_model: helloollel/Llama-3.1-8B-instruct-bilibili
+language:
+- en
+library_name: transformers
+license: apache-2.0
+quantized_by: mradermacher
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+- sft
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags:  -->
+static quants of https://huggingface.co/helloollel/Llama-3.1-8B-instruct-bilibili
+
+<!-- provided-files -->
+weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
+## 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-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q2_K.gguf) | Q2_K | 3.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.IQ3_XS.gguf) | IQ3_XS | 3.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q3_K_S.gguf) | Q3_K_S | 3.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.IQ3_M.gguf) | IQ3_M | 3.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q3_K_L.gguf) | Q3_K_L | 4.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.IQ4_XS.gguf) | IQ4_XS | 4.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q5_K_S.gguf) | Q5_K_S | 5.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q5_K_M.gguf) | Q5_K_M | 5.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-bilibili-GGUF/resolve/main/Llama-3.1-8B-instruct-bilibili.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
+
+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.
+
+<!-- end -->