Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,21 @@ saved_model/**/* 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
+MiniMA-2-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniMA-2-3B-f16.gguf filter=lfs diff=lfs merge=lfs -text

MiniMA-2-3B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b825e5ae63583dc61ba25d6af1287beeb0f5568ebdab761a661f2f7c9fdfb32
+size 1297187936

MiniMA-2-3B-Q3_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ad7723ccfb80402f9e9c58f7c315ee485a201be525427e071eb24e2ca172c0
+size 1507578464

MiniMA-2-3B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e58fb3cc55e5f18931e3362dfc4067afdbde98ad1bf35d166ae850d7bfe2b86
+size 1631048288

MiniMA-2-3B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ad7723ccfb80402f9e9c58f7c315ee485a201be525427e071eb24e2ca172c0
+size 1507578464

MiniMA-2-3B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9455d900df1a24da51ee67f3bac9bcca729bdd426468ac296f712f2c784792
+size 1358549600

MiniMA-2-3B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9773553da9001bc733a2429022096f2028cdda6f0568e7dea5be8b1c54adc9
+size 1739602016

MiniMA-2-3B-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39ccdbb7cb17d40924b3c4601c09885764dc9ed7dc7191eea70c149d2beb039
+size 1918920800

MiniMA-2-3B-Q4_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b72cfc709c53664e725bb84fa57b8f631670960a46aded0d25d2aa22aebe41
+size 1846655072

MiniMA-2-3B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b72cfc709c53664e725bb84fa57b8f631670960a46aded0d25d2aa22aebe41
+size 1846655072

MiniMA-2-3B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6c666583cc666413f086200bd0264f5adf8fb75abd0560cc04c50e0072baad
+size 1756903520

MiniMA-2-3B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d847b35f8500782418461d6f89e37beb0cea67d960629a0cfc5987f4c7a2d01
+size 2098239584

MiniMA-2-3B-Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528a74a27e05080ef9787431f64d6963e1facad90aea418380d2b6ba8f8c906b
+size 2277558368

MiniMA-2-3B-Q5_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede793da2b0b652ab4e4692407c8b9a6ab3c6bf4b8b278eb1ca4a855f78d94e5
+size 2153388128

MiniMA-2-3B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede793da2b0b652ab4e4692407c8b9a6ab3c6bf4b8b278eb1ca4a855f78d94e5
+size 2153388128

MiniMA-2-3B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3e753370aeecbcbbdd5f4bf7e38d5045de1b96328519cdc4e83f6be9fd22edf
+size 2098239584

MiniMA-2-3B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b29d745d386b974991a46d9ca1bdc96cb07c45a6c5615d2d065ad108c4a4f7
+size 2479292000

MiniMA-2-3B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c1cfb7d853accd06b6f5b07b5b760547a5598cf5ffe814446ca94852d337f7
+size 3210768992

MiniMA-2-3B-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4211a5597771040961e17636fdca599f1eeeba382a96a4ae746c821cda916823
+size 6042292800

README.md

@@ -68,7 +68,7 @@ The following clients/libraries will automatically download models for you, prov
 
 ### In `text-generation-webui`
 
-Under Download Model, you can enter the model repo: andrijdavid/MiniMA-2-3B-GGUF and below it, a specific filename to download, such as: MiniMA-2-3B.gguf.
+Under Download Model, you can enter the model repo: andrijdavid/MiniMA-2-3B-GGUF and below it, a specific filename to download, such as: MiniMA-2-3B-f16.gguf.
 
 Then click Download.
 
@@ -83,7 +83,7 @@ pip3 install huggingface-hub
 Then you can download any individual model file to the current directory, at high speed, with a command like this:
 
 ```shell
-huggingface-cli download andrijdavid/MiniMA-2-3B-GGUF MiniMA-2-3B.gguf --local-dir . --local-dir-use-symlinks False
+huggingface-cli download andrijdavid/MiniMA-2-3B-GGUF MiniMA-2-3B-f16.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
 <details>
@@ -106,7 +106,7 @@ pip3 install hf_transfer
 And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
 
 ```shell
-HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download andrijdavid/MiniMA-2-3B-GGUF MiniMA-2-3B.gguf --local-dir . --local-dir-use-symlinks False
+HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download andrijdavid/MiniMA-2-3B-GGUF MiniMA-2-3B-f16.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
 Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
@@ -118,7 +118,7 @@ Windows Command Line users: You can set the environment variable by running `set
 Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 
 ```shell
-./main -ngl 35 -m MiniMA-2-3B.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>"
+./main -ngl 35 -m MiniMA-2-3B-f16.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>"
 ```
 
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
@@ -169,7 +169,7 @@ pip install llama-cpp-python
 from llama_cpp import Llama
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
 llm = Llama(
-  model_path="./MiniMA-2-3B.gguf",  # Download the model file first
+  model_path="./MiniMA-2-3B-f16.gguf",  # Download the model file first
   n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources
   n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
   n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
@@ -182,7 +182,7 @@ output = llm(
   echo=True        # Whether to echo the prompt
 )
 # Chat Completion API
-llm = Llama(model_path="./MiniMA-2-3B.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
+llm = Llama(model_path="./MiniMA-2-3B-f16.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
 llm.create_chat_completion(
     messages = [
         {"role": "system", "content": "You are a story writing assistant."},