TheBloke
/

OpenOrcaxOpenChat-Preview2-13B-GGML

Text Generation

Transformers

English

llama

Model card Files Files and versions

xet

Community

TheBloke commited on Aug 3, 2023

Commit

b84e95c

1 Parent(s): 50da52a

Initial GGML model commit

Browse files

Files changed (1) hide show

README.md +16 -16

README.md CHANGED Viewed

@@ -89,20 +89,20 @@ Refer to the Provided Files table below to see what files use which methods, and
 | Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
-| openorcaxopenchat-preview2-13b.ggmlv3.q2_K.bin | q2_K | 2 | 5.74 GB| 8.24 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
-| openorcaxopenchat-preview2-13b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 7.14 GB| 9.64 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
-| openorcaxopenchat-preview2-13b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.53 GB| 9.03 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
-| openorcaxopenchat-preview2-13b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.87 GB| 8.37 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
-| openorcaxopenchat-preview2-13b.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB| 9.82 GB | Original quant method, 4-bit. |
-| openorcaxopenchat-preview2-13b.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB| 10.64 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
-| openorcaxopenchat-preview2-13b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 8.06 GB| 10.56 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
-| openorcaxopenchat-preview2-13b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.56 GB| 10.06 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
-| openorcaxopenchat-preview2-13b.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB| 11.45 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
-| openorcaxopenchat-preview2-13b.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB| 12.26 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
-| openorcaxopenchat-preview2-13b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.40 GB| 11.90 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
-| openorcaxopenchat-preview2-13b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 9.14 GB| 11.64 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
-| openorcaxopenchat-preview2-13b.ggmlv3.q6_K.bin | q6_K | 6 | 10.83 GB| 13.33 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
-| openorcaxopenchat-preview2-13b.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB| 16.33 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
 **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
@@ -163,7 +163,7 @@ Thank you to all my generous patrons and donaters!
 # OpenOrca x OpenChat - Preview2 - 13B
-We have used our own [OpenOrca dataset](https://huggingface.co/datasets/Open-Orca/OpenOrca) to fine-tune Llama2-13B using [OpenChat](https://huggingface.co/openchat) packing and conditional behavior cloning.
 This dataset is our attempt to reproduce the dataset generated for Microsoft Research's [Orca Paper](https://arxiv.org/abs/2306.02707).
 This second preview release is trained on a curated filtered subset of most of our GPT-4 augmented data.
@@ -175,7 +175,7 @@ As well, this is done with <1/10th the compute requirement and using <20% of the
 We have run extensive evaluations internally and expect this model to **place number 1** on both the HuggingFaceH4 Open LLM Leaderboard and the GPT4ALL Leaderboard for 13B models.
 "One" of [OpenChat](https://huggingface.co/openchat) has joined our team, and we'd like to provide special thanks for their training of this model!
-We have utilized OpenChat conditional behavior cloning and [MultiPack algorithm](https://github.com/imoneoi/multipack_sampler) which achieves 99.85% bin-packing efficiency on our dataset.
 This has significantly reduced training time, with efficiency improvement of 3-10X over traditional methods.

 | Name | Quant method | Bits | Size | Max RAM required | Use case |
 | ---- | ---- | ---- | ---- | ---- | ----- |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q2_K.bin) | q2_K | 2 | 5.74 GB| 8.24 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 7.14 GB| 9.64 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 6.53 GB| 9.03 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 5.87 GB| 8.37 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q4_0.bin) | q4_0 | 4 | 7.32 GB| 9.82 GB | Original quant method, 4-bit. |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q4_1.bin) | q4_1 | 4 | 8.14 GB| 10.64 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 8.06 GB| 10.56 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 7.56 GB| 10.06 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q5_0.bin) | q5_0 | 5 | 8.95 GB| 11.45 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q5_1.bin) | q5_1 | 5 | 9.76 GB| 12.26 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 9.40 GB| 11.90 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 9.14 GB| 11.64 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q6_K.bin) | q6_K | 6 | 10.83 GB| 13.33 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization |
+| [openorcaxopenchat-preview2-13b.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/OpenOrcaxOpenChat-Preview2-13B-GGML/blob/main/openorcaxopenchat-preview2-13b.ggmlv3.q8_0.bin) | q8_0 | 8 | 13.83 GB| 16.33 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
 **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
 # OpenOrca x OpenChat - Preview2 - 13B
+We have used our own [OpenOrca dataset](https://huggingface.co/datasets/Open-Orca/OpenOrca) to fine-tune Llama2-13B using [OpenChat](https://huggingface.co/openchat) packing.
 This dataset is our attempt to reproduce the dataset generated for Microsoft Research's [Orca Paper](https://arxiv.org/abs/2306.02707).
 This second preview release is trained on a curated filtered subset of most of our GPT-4 augmented data.
 We have run extensive evaluations internally and expect this model to **place number 1** on both the HuggingFaceH4 Open LLM Leaderboard and the GPT4ALL Leaderboard for 13B models.
 "One" of [OpenChat](https://huggingface.co/openchat) has joined our team, and we'd like to provide special thanks for their training of this model!
+We have utilized OpenChat [MultiPack algorithm](https://github.com/imoneoi/multipack_sampler) which achieves 99.85% bin-packing efficiency on our dataset.
 This has significantly reduced training time, with efficiency improvement of 3-10X over traditional methods.