初始化项目，由ModelHub XC社区提供模型

Model: bartowski/AMD-Llama-135m-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,53 @@
+*.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
+AMD-Llama-135m-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+AMD-Llama-135m-f16.gguf filter=lfs diff=lfs merge=lfs -text

AMD-Llama-135m-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043b07e1c0dce4ad222318bdc3370513e974878c015c0d08a39ff6e2f1c278d3
+size 70112256

AMD-Llama-135m-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c3ff285ea9ffe49fc3999979a26a35e4145ea77c084b29869c352f0d571a7d
+size 79145472

AMD-Llama-135m-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d65ff86fec000b3c95b70ce21f1fdc36ab6bdbbbe468701558ed1d0e37b437b
+size 76538880

AMD-Llama-135m-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101d49c219205cae144ce90b16ad1ce0c51fa1e5a046a58b1a0f1786008c39de
+size 98042880

AMD-Llama-135m-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2b8e2176887595a33aceace7e52fe7abffac335640effda0596946155a3113
+size 82665984

AMD-Llama-135m-Q4_0_4_4.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec83e9085a3edbcc90ee164a8d244332f62604ba88b3b8a98c870ebe7e62b3af
+size 82567680

AMD-Llama-135m-Q4_0_4_8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c079203f0117efb4d3497f294f42267888fc7a4466957bd515d01f07cc18d035
+size 82567680

AMD-Llama-135m-Q4_0_8_8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75fbdbfa50c4c002ecfae0037fc477718127763a1d9848532e52bc9c4a137a0b
+size 82567680

AMD-Llama-135m-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52468e3f60ecc73a709a09a8da9510ae256ef56f1bb72ec4c6f45d8bbf3dfb4
+size 104153088

AMD-Llama-135m-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e159cfb17015e6e923a3b2930c8678db7c8420631d4117096c7c7795cbbcc180
+size 85913088

AMD-Llama-135m-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0385c2b7f0acfeb27a09e2a4528c3a0cb66d23f46ce8201b69b755ac85ce840a
+size 83059200

AMD-Llama-135m-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520e7d146bf377c717de23f89b4320eeac7d3d3eefc8c516e5a8e93ac07598e7
+size 113147904

AMD-Llama-135m-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73f41662f6bf6d7faf5b5802fcfc167339a32289d248d53d65d5146d44433b6
+size 97979904

AMD-Llama-135m-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da39564e255fa1bf4eda602aa3c91ad38c50bbb66c75cb84dcdfb9c03e623c3
+size 96256512

AMD-Llama-135m-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6aee80ad703fa3b7aac9c690f7902ef57c9a053e6e65d361a688dd5fe71f45
+size 110800896

AMD-Llama-135m-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cb1cdacab92172144e1f2de676622b50abab4929c365ae32517c6e379fa0381
+size 122704896

AMD-Llama-135m-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caebd1a674018ee29fff99681239878ff45f955db6c0ad1ee9f156dbc5f99f73
+size 143275008

AMD-Llama-135m-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7941d581c2fc6a77726b1be2ff64213c02b8aedffd63d18c9b425410b34c07b0
+size 268980960

README.md

@@ -0,0 +1,116 @@
+---
+base_model: amd/AMD-Llama-135m
+datasets:
+- cerebras/SlimPajama-627B
+- manu/project_gutenberg
+license: apache-2.0
+pipeline_tag: text-generation
+quantized_by: bartowski
+---
+
+## Llamacpp imatrix Quantizations of AMD-Llama-135m
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3825">b3825</a> for quantization.
+
+Original model: https://huggingface.co/amd/AMD-Llama-135m
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
+## Prompt format
+
+No prompt format found, check original model page
+
+## Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Split | Description |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [AMD-Llama-135m-f16.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-f16.gguf) | f16 | 0.27GB | false | Full F16 weights. |
+| [AMD-Llama-135m-Q8_0.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q8_0.gguf) | Q8_0 | 0.14GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [AMD-Llama-135m-Q6_K_L.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q6_K_L.gguf) | Q6_K_L | 0.12GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [AMD-Llama-135m-Q6_K.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q6_K.gguf) | Q6_K | 0.11GB | false | Very high quality, near perfect, *recommended*. |
+| [AMD-Llama-135m-Q5_K_L.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q5_K_L.gguf) | Q5_K_L | 0.11GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [AMD-Llama-135m-Q5_K_M.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q5_K_M.gguf) | Q5_K_M | 0.10GB | false | High quality, *recommended*. |
+| [AMD-Llama-135m-Q5_K_S.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q5_K_S.gguf) | Q5_K_S | 0.10GB | false | High quality, *recommended*. |
+| [AMD-Llama-135m-Q4_K_L.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q4_K_L.gguf) | Q4_K_L | 0.10GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [AMD-Llama-135m-Q3_K_XL.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q3_K_XL.gguf) | Q3_K_XL | 0.10GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [AMD-Llama-135m-Q4_K_M.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q4_K_M.gguf) | Q4_K_M | 0.09GB | false | Good quality, default size for must use cases, *recommended*. |
+| [AMD-Llama-135m-Q4_K_S.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q4_K_S.gguf) | Q4_K_S | 0.08GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [AMD-Llama-135m-Q4_0_8_8.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q4_0_8_8.gguf) | Q4_0_8_8 | 0.08GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
+| [AMD-Llama-135m-Q4_0_4_8.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q4_0_4_8.gguf) | Q4_0_4_8 | 0.08GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
+| [AMD-Llama-135m-Q4_0_4_4.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q4_0_4_4.gguf) | Q4_0_4_4 | 0.08GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
+| [AMD-Llama-135m-Q4_0.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q4_0.gguf) | Q4_0 | 0.08GB | false | Legacy format, generally not worth using over similarly sized formats |
+| [AMD-Llama-135m-IQ4_XS.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-IQ4_XS.gguf) | IQ4_XS | 0.08GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [AMD-Llama-135m-Q3_K_L.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-Q3_K_L.gguf) | Q3_K_L | 0.08GB | false | Lower quality but usable, good for low RAM availability. |
+| [AMD-Llama-135m-IQ3_M.gguf](https://huggingface.co/bartowski/AMD-Llama-135m-GGUF/blob/main/AMD-Llama-135m-IQ3_M.gguf) | IQ3_M | 0.07GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+
+## Embed/output weights
+
+Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
+
+Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
+
+Thanks!
+
+## Downloading using huggingface-cli
+
+First, make sure you have hugginface-cli installed:
+
+```
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, you can target the specific file you want:
+
+```
+huggingface-cli download bartowski/AMD-Llama-135m-GGUF --include "AMD-Llama-135m-Q4_K_M.gguf" --local-dir ./
+```
+
+If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
+
+```
+huggingface-cli download bartowski/AMD-Llama-135m-GGUF --include "AMD-Llama-135m-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (AMD-Llama-135m-Q8_0) or download them all in place (./)
+
+## Q4_0_X_X
+
+These are *NOT* for Metal (Apple) offloading, only ARM chips.
+
+If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
+
+To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
+
+## Which file should I choose?
+
+A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
+
+The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
+
+If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
+
+If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
+
+Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+
+If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
+
+If you want to get more into the weeds, you can check out this extremely useful feature chart:
+
+[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
+
+But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+
+These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+
+The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
+
+## Credits
+
+Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
+
+Thank you ZeroWw for the inspiration to experiment with embed/output
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}