measurement.json

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: 01-ai/Yi-1.5-34B
+tags:
+- generated_from_trainer
+- axolotl
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- microsoft/orca-math-word-problems-200k
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Exllama v2 Quantizations of dolphin-2.9.1-yi-1.5-34b
+
+Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.21">turboderp's ExLlamaV2 v0.0.21</a> for quantization.
+
+<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
+
+Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
+
+Original model: https://huggingface.co/cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
+
+## Prompt format
+
+```
+<|im_start|> system
+{system_prompt}<|im_end|> 
+<|im_start|> user
+{prompt}<|im_end|> 
+<|im_start|> assistant
+
+```
+
+## Available sizes
+
+| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
+| ------ | ---- | ------------ | ---- | ---- | ---- | ----------- |
+| [8_0](https://huggingface.co/bartowski/dolphin-2.9.1-yi-1.5-34b-exl2/tree/8_0)   | 8.0  | 8.0 | 34.9 GB | 37.6 GB | 41.6 GB | Max quality producable by ExLlamav2, generally unneeded but maximum performance      |
+| [6_5](https://huggingface.co/bartowski/dolphin-2.9.1-yi-1.5-34b-exl2/tree/6_5)   | 6.5  | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, **recommended**.       |
+| [5_0](https://huggingface.co/bartowski/dolphin-2.9.1-yi-1.5-34b-exl2/tree/5_0)   | 5.0  | 8.0 | 22.6 GB | 25.3 GB | 29.3 GB | Very high quality, usable at 4k context on 24GB.       |
+| [4_25](https://huggingface.co/bartowski/dolphin-2.9.1-yi-1.5-34b-exl2/tree/4_25) | 4.25 | 6.0 | 19.5 GB | 22.2 GB | 26.2 GB | GPTQ equivalent bits per weight, slightly higher quality.                   |
+| [3_5](https://huggingface.co/bartowski/dolphin-2.9.1-yi-1.5-34b-exl2/tree/3_5)   | 3.5  | 6.0 | 16.5 GB | 19.2 GB | 23.2 GB | Lower quality, only use if you have to.                                     |
+| [3_0](https://huggingface.co/bartowski/dolphin-2.9.1-yi-1.5-34b-exl2/tree/3_0)   | 3.0  | 6.0 | 14.3 GB | 17.0 GB | 21.0 GB | Very low quality, usable with 16gb of VRAM. |
+
+## Download instructions
+
+With git:
+
+```shell
+git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/dolphin-2.9.1-yi-1.5-34b-exl2 dolphin-2.9.1-yi-1.5-34b-exl2-6_5
+```
+
+With huggingface hub (credit to TheBloke for instructions):
+
+```shell
+pip3 install huggingface-hub
+```
+
+To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
+
+Linux:
+
+```shell
+huggingface-cli download bartowski/dolphin-2.9.1-yi-1.5-34b-exl2 --revision 6_5 --local-dir dolphin-2.9.1-yi-1.5-34b-exl2-6_5 --local-dir-use-symlinks False
+```
+
+Windows (which apparently doesn't like _ in folders sometimes?):
+
+```shell
+huggingface-cli download bartowski/dolphin-2.9.1-yi-1.5-34b-exl2 --revision 6_5 --local-dir dolphin-2.9.1-yi-1.5-34b-exl2-6.5 --local-dir-use-symlinks False
+```
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski