diff --git a/.gitattributes b/.gitattributes index a6344aa..7eeeb81 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,15 @@ 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 +llama-3-8b-gpt-4o-ru1.0-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-gpt-4o-ru1.0-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9e237f8 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +license: llama3 +base_model: ruslandev/llama-3-8b-gpt-4o-ru1.0 +tags: +- generated_from_trainer +- TensorBlock +- GGUF +datasets: +- ruslandev/tagengo-rus-gpt-4o +model-index: +- name: home/ubuntu/llm_training/axolotl/llama3-8b-gpt-4o-ru/output_llama3_8b_gpt_4o_ru + results: [] +--- + +
+TensorBlock +
+
+
+

+ Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server +

+
+
+ +## ruslandev/llama-3-8b-gpt-4o-ru1.0 - GGUF + +This repo contains GGUF format model files for [ruslandev/llama-3-8b-gpt-4o-ru1.0](https://huggingface.co/ruslandev/llama-3-8b-gpt-4o-ru1.0). + +The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d). + +
+ + Run them on the TensorBlock client using your local machine ↗ + +
+ +## Prompt template + +``` +<|begin_of_text|><|start_header_id|>system<|end_header_id|> + +{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> +``` + +## Model file specification + +| Filename | Quant type | File Size | Description | +| -------- | ---------- | --------- | ----------- | +| [llama-3-8b-gpt-4o-ru1.0-Q2_K.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes | +| [llama-3-8b-gpt-4o-ru1.0-Q3_K_S.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q3_K_S.gguf) | Q3_K_S | 3.664 GB | very small, high quality loss | +| [llama-3-8b-gpt-4o-ru1.0-Q3_K_M.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss | +| [llama-3-8b-gpt-4o-ru1.0-Q3_K_L.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss | +| [llama-3-8b-gpt-4o-ru1.0-Q4_0.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M | +| [llama-3-8b-gpt-4o-ru1.0-Q4_K_S.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss | +| [llama-3-8b-gpt-4o-ru1.0-Q4_K_M.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended | +| [llama-3-8b-gpt-4o-ru1.0-Q5_0.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M | +| [llama-3-8b-gpt-4o-ru1.0-Q5_K_S.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended | +| [llama-3-8b-gpt-4o-ru1.0-Q5_K_M.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended | +| [llama-3-8b-gpt-4o-ru1.0-Q6_K.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss | +| [llama-3-8b-gpt-4o-ru1.0-Q8_0.gguf](https://huggingface.co/tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF/blob/main/llama-3-8b-gpt-4o-ru1.0-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended | + + +## Downloading instruction + +### Command line + +Firstly, install Huggingface Client + +```shell +pip install -U "huggingface_hub[cli]" +``` + +Then, downoad the individual model file the a local directory + +```shell +huggingface-cli download tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF --include "llama-3-8b-gpt-4o-ru1.0-Q2_K.gguf" --local-dir MY_LOCAL_DIR +``` + +If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try: + +```shell +huggingface-cli download tensorblock/llama-3-8b-gpt-4o-ru1.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf' +``` diff --git a/llama-3-8b-gpt-4o-ru1.0-Q2_K.gguf b/llama-3-8b-gpt-4o-ru1.0-Q2_K.gguf new file mode 100644 index 0000000..032ea6e --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef06e59ca3d4f66d3c5e45e4c9dd53fb60e8395843141adef3f70166ce46e8d +size 3179131904 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q3_K_L.gguf b/llama-3-8b-gpt-4o-ru1.0-Q3_K_L.gguf new file mode 100644 index 0000000..436a476 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:340d1267763cab5f6bf59e7c4cc2125f4ccdad9ca84bdeb94fe303035e82667d +size 4321956864 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q3_K_M.gguf b/llama-3-8b-gpt-4o-ru1.0-Q3_K_M.gguf new file mode 100644 index 0000000..80873a0 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be325cd993fe561f130b7c970b4625c6f95290259d1679276d8c8ab895dc93b9 +size 4018918400 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q3_K_S.gguf b/llama-3-8b-gpt-4o-ru1.0-Q3_K_S.gguf new file mode 100644 index 0000000..6b0bef4 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fda71b46a1734f655131a741793f9756a9e90744c269321d8d40f6b44ac7a2 +size 3664499712 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q4_0.gguf b/llama-3-8b-gpt-4o-ru1.0-Q4_0.gguf new file mode 100644 index 0000000..9a46cf5 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:675ae3a1898d8c61a0fd5aa006576ead250de72e0832dda060360a1fb018ab49 +size 4661212160 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q4_K_M.gguf b/llama-3-8b-gpt-4o-ru1.0-Q4_K_M.gguf new file mode 100644 index 0000000..b027c07 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c9c0b8dcb94184774a13d5b71ec1ed3a50827a6be9f1e325167e2afacad1b0 +size 4920734720 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q4_K_S.gguf b/llama-3-8b-gpt-4o-ru1.0-Q4_K_S.gguf new file mode 100644 index 0000000..df5db33 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dcd4803fd7615bd7c688cb13f59277844116d144dffa9b853e78c1f710914a0 +size 4692669440 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q5_0.gguf b/llama-3-8b-gpt-4o-ru1.0-Q5_0.gguf new file mode 100644 index 0000000..12e7f20 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:727a5a8e7e38c33539215984ce43ca7d8175ef0605b622767c326037d127d7cd +size 5599294464 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q5_K_M.gguf b/llama-3-8b-gpt-4o-ru1.0-Q5_K_M.gguf new file mode 100644 index 0000000..5d81947 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e6e8dedc1873c0e061a0b914e17f23892958e305e29d6c4c216491cb6dc2f7 +size 5732987904 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q5_K_S.gguf b/llama-3-8b-gpt-4o-ru1.0-Q5_K_S.gguf new file mode 100644 index 0000000..3e23ef2 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:357197ce6877199c780661e5b383760b4fbb450751265edec4acb8ea18792af5 +size 5599294464 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q6_K.gguf b/llama-3-8b-gpt-4o-ru1.0-Q6_K.gguf new file mode 100644 index 0000000..3da761d --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8fb37f6da24f82689ec2a5361ebef5c7eadfffb1582861c7967cde6fa9e06a +size 6596006912 diff --git a/llama-3-8b-gpt-4o-ru1.0-Q8_0.gguf b/llama-3-8b-gpt-4o-ru1.0-Q8_0.gguf new file mode 100644 index 0000000..72b5098 --- /dev/null +++ b/llama-3-8b-gpt-4o-ru1.0-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4954d6825d8a97c8a32897c0207a79caa93877741395dc672c187f50b05ad17d +size 8540771328