Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: CausalLM/14B
|
| 3 |
+
datasets:
|
| 4 |
+
- JosephusCheung/GuanacoDataset
|
| 5 |
+
- Open-Orca/OpenOrca
|
| 6 |
+
- stingning/ultrachat
|
| 7 |
+
- meta-math/MetaMathQA
|
| 8 |
+
- liuhaotian/LLaVA-Instruct-150K
|
| 9 |
+
- jondurbin/airoboros-3.1
|
| 10 |
+
- WizardLM/WizardLM_evol_instruct_V2_196k
|
| 11 |
+
- RyokoAI/ShareGPT52K
|
| 12 |
+
- RyokoAI/Fandom23K
|
| 13 |
+
- milashkaarshif/MoeGirlPedia_wikitext_raw_archive
|
| 14 |
+
- wikipedia
|
| 15 |
+
- wiki_lingua
|
| 16 |
+
- fnlp/moss-003-sft-data
|
| 17 |
+
- garage-bAInd/Open-Platypus
|
| 18 |
+
- LDJnr/Puffin
|
| 19 |
+
- openbmb/llava_zh
|
| 20 |
+
- BAAI/COIG
|
| 21 |
+
- TigerResearch/tigerbot-zhihu-zh-10k
|
| 22 |
+
- liwu/MNBVC
|
| 23 |
+
- teknium/openhermes
|
| 24 |
+
inference: false
|
| 25 |
+
language:
|
| 26 |
+
- en
|
| 27 |
+
- zh
|
| 28 |
+
license: wtfpl
|
| 29 |
+
model_creator: CausalLM
|
| 30 |
+
model_name: CausalLM 14B
|
| 31 |
+
model_type: llama
|
| 32 |
+
pipeline_tag: text-generation
|
| 33 |
+
prompt_template: '<|im_start|>system
|
| 34 |
+
{system_message}<|im_end|>
|
| 35 |
+
<|im_start|>user
|
| 36 |
+
{prompt}<|im_end|>
|
| 37 |
+
<|im_start|>assistant
|
| 38 |
+
'
|
| 39 |
+
quantized_by: cgus
|
| 40 |
+
tags:
|
| 41 |
+
- llama
|
| 42 |
+
- llama2
|
| 43 |
+
---
|
| 44 |
+
# CausalLM 14B - GPTQ
|
| 45 |
+
- Model creator: [CausalLM](https://huggingface.co/CausalLM)
|
| 46 |
+
- Original model: [CausalLM 14B](https://huggingface.co/CausalLM/14B)
|
| 47 |
+
|
| 48 |
+
<!-- description start -->
|
| 49 |
+
## Description
|
| 50 |
+
|
| 51 |
+
Experimental exl2 quantization for CausalLM-14B for Exllamav2.
|
| 52 |
+
I had some issues during quantization process, so I suspect it might have quality issues.
|
| 53 |
+
3.5bpw version barely fits 12GB VRAM but has unusually high perplexity for wikitext dataset.
|
| 54 |
+
I couldn't measure perplexity for 4bpw version and to compare it with TheBloke's GPTQ, so I have no idea if my quantization has issues or it supposed to be like this.
|
| 55 |
+
|
| 56 |
+
You could try this exl2 version but I'd recommend to use [TheBloke's GPTQ](https://huggingface.co/TheBloke/CausalLM-14B-GPTQ) version instead.
|