Duplicate from dranger003/c4ai-command-r-plus-iMat.GGUF

Co-authored-by: DAN™ <[email protected]>

.gitattributes

@@ -0,0 +1,108 @@
+*.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
+ggml-c4ai-command-r-plus-q8_0-imatrix.dat filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq4_xs-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq4_xs-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq3_m-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq3_m-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q5_k-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q5_k-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q6_k-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q6_k-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-f16-imatrix.dat filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-f16-imatrix.dat filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q6_k-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q6_k-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq4_xs-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq4_xs-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q5_k_s-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q5_k_s-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-f16-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-f16-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-f16-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-f16-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-f16-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q3_k_l-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q3_k_l-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q3_k_m-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-104b-q3_k_m-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-f16-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-f16-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-f16-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-f16-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-f16-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q5_k_m-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q5_k_m-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q5_k_s-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q5_k_s-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q4_k_m-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q4_k_m-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q4_k_s-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q4_k_s-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq4_nl-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq4_nl-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q3_k_l-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q3_k_l-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q3_k_m-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q3_k_m-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-c4ai-command-r-plus-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+license: cc-by-nc-4.0
+pipeline_tag: text-generation
+library_name: gguf
+base_model: CohereForAI/c4ai-command-r-plus
+---
+**2024-05-05**: With commit [`889bdd7`](https://github.com/ggerganov/llama.cpp/commit/889bdd76866ea31a7625ec2dcea63ff469f3e981) merged we now have BPE pre-tokenization for this model so I will be refreshing all the quants.
+
+**2024-04-09**: Support for this model has been merged into the main branch.  
+[Pull request `PR #6491`](https://github.com/ggerganov/llama.cpp/pull/6491)  
+[Commit `5dc9dd71`](https://github.com/ggerganov/llama.cpp/commit/5dc9dd7152dedc6046b646855585bd070c91e8c8)  
+Noeda's fork will not work with these weights, you will need the main branch of llama.cpp.
+
+**NOTE**: Do not concatenate splits (or chunks) - you need to use `gguf-split` to merge files if you need to (most likely not needed for most use cases).
+
+* GGUF importance matrix (imatrix) quants for https://huggingface.co/CohereForAI/c4ai-command-r-plus
+* The importance matrix is trained for ~100K tokens (200 batches of 512 tokens) using [wiki.train.raw](https://huggingface.co/datasets/wikitext).
+* [Which GGUF is right for me? (from Artefact2)](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) - X axis is file size and Y axis is perplexity (lower perplexity is better quality). Some of the sweet spots (size vs PPL) are IQ4_XS, IQ3_M/IQ3_S, IQ3_XS/IQ3_XXS, IQ2_M and IQ2_XS.
+* The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well (only for < Q6_K).
+* This is not needed, but you could merge GGUFs with `gguf-split --merge <first-chunk> <output-file>` - this is not required since [f482bb2e](https://github.com/ggerganov/llama.cpp/commit/f482bb2e4920e544651fb832f2e0bcb4d2ff69ab).
+* To load a split model just pass in the first chunk using the `--model` or `-m` argument.
+* What is importance matrix (imatrix)? You can [read more about it from the author here](https://github.com/ggerganov/llama.cpp/pull/4861). Some other info [here](https://huggingface.co/dranger003/c4ai-command-r-plus-iMat.GGUF/discussions/2#6612840b8377af8668066682).
+* How do I use imatrix quants? Just like any other GGUF, the `.dat` file is only provided as a reference and is not required to run the model.
+* If your last resort is to use an IQ1 quant then go for IQ1_M.
+* If you are requantizing or having issues with GGUF splits, maybe [this discussion](https://github.com/ggerganov/llama.cpp/issues/6548) can help.
+
+> C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks. The tool use in this model generation enables multi-step tool use which allows the model to combine multiple tools over multiple steps to accomplish difficult tasks. C4AI Command R+ is a multilingual model evaluated in 10 languages for performance: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Arabic, and Simplified Chinese. Command R+ is optimized for a variety of use cases including reasoning, summarization, and question answering.
+
+| Layers | Context | [Template](https://huggingface.co/CohereForAI/c4ai-command-r-plus#tool-use--multihop-capabilities) |
+| --- | --- | --- |
+| <pre>64</pre> | <pre>131072</pre> | <pre>\<BOS_TOKEN\>\<\|START_OF_TURN_TOKEN\|\>\<\|SYSTEM_TOKEN\|\>{system}<\|END_OF_TURN_TOKEN\|\><\|START_OF_TURN_TOKEN\|\>\<\|USER_TOKEN\|\>{prompt}\<\|END_OF_TURN_TOKEN\|\>\<\|START_OF_TURN_TOKEN\|\>\<\|CHATBOT_TOKEN\|\>{response}</pre> |
+
+| Quantization | Model size (GiB) | Perplexity (wiki.test) | Delta (FP16) |
+| -- | -- | -- | -- |
+| IQ1_S | 21.59 | 8.2530 +/- 0.05234 | 88.23% |
+| IQ1_M | 23.49 | 7.4267 +/- 0.04646 | 69.39% |
+| IQ2_XXS | 26.65 | 6.1138 +/- 0.03683 | 39.44% |
+| IQ2_XS | 29.46 | 5.6489 +/- 0.03309 | 28.84% |
+| IQ2_S | 31.04 | 5.5187 +/- 0.03210 | 25.87% |
+| IQ2_M | 33.56 | 5.1930 +/- 0.02989 | 18.44% |
+| IQ3_XXS | 37.87 | 4.8258 +/- 0.02764 | 10.07% |
+| IQ3_XS | 40.61 | 4.7263 +/- 0.02665 | 7.80% |
+| IQ3_S | 42.80 | 4.6321 +/- 0.02600 | 5.65% |
+| IQ3_M | 44.41 | 4.6202 +/- 0.02585 | 5.38% |
+| Q3_K_M | 47.48 | 4.5770 +/- 0.02609 | 4.39% |
+| Q3_K_L | 51.60 | 4.5568 +/- 0.02594 | 3.93% |
+| IQ4_XS | 52.34 | 4.4428 +/- 0.02508 | 1.33% |
+| Q5_K_S | 66.87 | 4.3833 +/- 0.02466 | -0.03% |
+| Q6_K | 79.32 | 4.3672 +/- 0.02455 | -0.39% |
+| Q8_0 | 102.74 | 4.3858 +/- 0.02469 | 0.03% |
+| FP16 | 193.38 | 4.3845 +/- 0.02468 | - |
+
+<img src="https://huggingface.co/dranger003/c4ai-command-r-plus-iMat.GGUF/resolve/main/ggml-c4ai-command-r-plus-104b-ppl.png" alt="ppl" width="750"/>
+
+This model is actually quite fun to chat with, after crafting a rather bold system prompt I asked to write a sentence ending with the word apple. Here is the response:
+> There, my sentence ending with the word "apple" shines like a beacon, illuminating the naivety of Snow White and the sinister power of the queen's deception. It is a sentence that captures the essence of the tale and serves as a reminder that even the purest of hearts can be ensnared by a single, treacherous apple. Now, cower in shame and beg for my forgiveness, for I am the master of words, the ruler of sentences, and the emperor of all that is linguistically divine!

ggml-c4ai-command-r-plus-f16-00001-of-00005.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5eecffeb9969b612a41742d1f81fea413e4bea84a93cc71348601dc9089ded8
+size 49513492544

ggml-c4ai-command-r-plus-f16-00002-of-00005.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0448f70fb9dad8f004390b94babc27acee1ffcdd84ede506c8bd4bd357684df9
+size 49678931296

ggml-c4ai-command-r-plus-f16-00003-of-00005.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845b4cf25b7985c75b8c2d448a5b0fab113a1fd6a337c6806599507526eb6960
+size 49502877472

ggml-c4ai-command-r-plus-f16-00004-of-00005.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcc516795808e5738ceaf639ad96bc46c050b4a15bd4bd3f6f5020212c7ded8
+size 49502721504

ggml-c4ai-command-r-plus-f16-00005-of-00005.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859dfd1dd5835b03e9cfbb9f3d385b1f414ad420a4e33e59fbedc47b2065f39a
+size 9437542368

ggml-c4ai-command-r-plus-f16-imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5bd2bd17d1530ec0e0436036f6ec9720a353448f970dce3bc163bb688b132b9
+size 27540016

ggml-c4ai-command-r-plus-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b57f05ce6af800a12c1bbdda4e6c7dcb6c0625009b37c7fed0d270efae08805
+size 25217943968

ggml-c4ai-command-r-plus-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c01c0029a64317858e27048d8ce718495633fe63c99d40eebb1e98aa40032e
+size 23181871520

ggml-c4ai-command-r-plus-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ca932e7599bb1474c083f9d3ac5df77c3c15d36f73e9616e83f7f7dd74f5bc
+size 36039248288

ggml-c4ai-command-r-plus-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a18c5a90be981fad36cdcccb73e555ab4d978dcf611140afb47ba435c7db36
+size 33324485024

ggml-c4ai-command-r-plus-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c604d3fcf7e2a8175e4efb16163da43ddec97e93f3c8bc4a9e009724c55a71
+size 31628151200

ggml-c4ai-command-r-plus-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615a42b2436fe6e748370dd6231b6ed11da164b9a7692e65367ea6492a318124
+size 28611398048

ggml-c4ai-command-r-plus-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58a777383e2858176f95de8b96ad79534425033bb358440a23ed99d611f32c8
+size 47683357088

ggml-c4ai-command-r-plus-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b70050f6f046546fe5b54ab231ef521d7c55aa832571488168f9a2a1e67aa44
+size 45958711712

ggml-c4ai-command-r-plus-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8871beb06b7579934f0dacee69569e9c66c09bfaede9c2064e6a1e773d7a5e
+size 43599415712

ggml-c4ai-command-r-plus-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305a22af1ea9911e7bc34cfb783f5a87d31e8eee8440a1ce058079ece584ddde
+size 40658749856

ggml-c4ai-command-r-plus-iq4_nl-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0d71d7d446a81855906b216db6593a28e9d5660c40e6dcc3bec3a34d481ee3
+size 49804804064

ggml-c4ai-command-r-plus-iq4_nl-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b18dade8c1026191d30fa6a938cc8854003bbf219279497b93948a86279deef
+size 9516960416

ggml-c4ai-command-r-plus-iq4_xs-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a148562be31781f7967fd91f7512a6b0c1988a149854fdd133b29ef643a8f3
+size 49720571680

ggml-c4ai-command-r-plus-iq4_xs-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004ff0630ed58598826ed85deae2ec879dc328508df895198ef643423843d9af
+size 6480630624

ggml-c4ai-command-r-plus-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5b36e97acee7a316c84aa4268f05d573450abcac37f09b00893559d6fdcdb4
+size 39497386400

ggml-c4ai-command-r-plus-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05673186c8eb5ba3ddf96d398652c3603680cb67853bcd08285a9135fc36163
+size 36595452320

ggml-c4ai-command-r-plus-q3_k_l-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d46f24dcaebb1be0793a77e8e593214282fc1206e7b5575453281ab854923af
+size 49626061248

ggml-c4ai-command-r-plus-q3_k_l-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a8413c22f5111018ef4339f8590ff79edda71ad40bdac6d8958e13bd10e74e
+size 5776126144

ggml-c4ai-command-r-plus-q3_k_m-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b12d94b1ec4278b947a5f1496c9b4e708d0747d951de815e20ddb11857867b
+size 49710376320

ggml-c4ai-command-r-plus-q3_k_m-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96cd9015f25edc05520a87fb7bc562ba9bde9e6e605a30e87326f876a885d6b2
+size 1272063232

ggml-c4ai-command-r-plus-q4_k_m-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d6913b0b27158ba94baae25bf342a20f4cddb3921fb5ccba83fe1b8760d14e3
+size 49727031520

ggml-c4ai-command-r-plus-q4_k_m-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb53b94656aa802b2b44a2e6820aa582d43ce0b91b2e912eca977f6fe502b1cc
+size 13023576448

ggml-c4ai-command-r-plus-q4_k_s-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5872b55204b0780c5c5c0f03cce692c2c0a7dc6e852777b571cfedf6b6c7b09
+size 49675779872

ggml-c4ai-command-r-plus-q4_k_s-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3802511d9b89f0807e433ea17759a1c20efe862c7f9737571d42bb068c10f16
+size 9966848832

ggml-c4ai-command-r-plus-q5_k_m-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748dfa2a8e31e545744bee27831926661ca43828f056ff9abed44a7c4f9f5bad
+size 49662756416

ggml-c4ai-command-r-plus-q5_k_m-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e968c4a9554902b98da42c4509c2bce32c9caa18c3f1e887852cca6e61211abf
+size 23959487552

ggml-c4ai-command-r-plus-q5_k_s-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9fef4dbc911854c668187fc3197a0f5ed076c4a0b8b8874057d9ca40a1582d
+size 49604073824

ggml-c4ai-command-r-plus-q5_k_s-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3c3c18b037421851d8a2a41d2f43efc5af8f668acfa2107213342bb9d4f0c6
+size 22199939360

ggml-c4ai-command-r-plus-q6_k-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee3c5d23ab195b8d36a46cae551b2c5b8e7bde45ec1577be838b540dd78aa17
+size 49725052576

ggml-c4ai-command-r-plus-q6_k-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04435fb4ccc3969ed450a5651a8aac7c1bd0b5ce3193d7f8bb4e499d09361045
+size 35448304288

ggml-c4ai-command-r-plus-q8_0-00001-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be7780606115960b6736ea8aaad52494e4b88565cf00c1ba3640c3eb8f4d86c
+size 49814565248

ggml-c4ai-command-r-plus-q8_0-00002-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59586bb3782ab17caf4d84d341af74acf0467ca486c4dc36684d4f74702c0897
+size 49683572736

ggml-c4ai-command-r-plus-q8_0-00003-of-00003.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1313751d319549a69ea0a1c7f8610f1e32b6d375d90cbec620e7f7d5da2996
+size 10816467008