Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned
|
3 |
+
datasets:
|
4 |
+
- gretelai/synthetic_text_to_sql
|
5 |
+
- HuggingFaceTB/cosmopedia
|
6 |
+
- teknium/OpenHermes-2.5
|
7 |
+
- Open-Orca/SlimOrca
|
8 |
+
- Open-Orca/OpenOrca
|
9 |
+
- cognitivecomputations/dolphin-coder
|
10 |
+
- databricks/databricks-dolly-15k
|
11 |
+
- yahma/alpaca-cleaned
|
12 |
+
- uonlp/CulturaX
|
13 |
+
- mwitiderrick/SwahiliPlatypus
|
14 |
+
- swahili
|
15 |
+
- Rogendo/English-Swahili-Sentence-Pairs
|
16 |
+
- ise-uiuc/Magicoder-Evol-Instruct-110K
|
17 |
+
- meta-math/MetaMathQA
|
18 |
+
- abacusai/ARC_DPO_FewShot
|
19 |
+
- abacusai/MetaMath_DPO_FewShot
|
20 |
+
- abacusai/HellaSwag_DPO_FewShot
|
21 |
+
- HaltiaAI/Her-The-Movie-Samantha-and-Theodore-Dataset
|
22 |
+
- HuggingFaceFW/fineweb
|
23 |
+
- occiglot/occiglot-fineweb-v0.5
|
24 |
+
- omi-health/medical-dialogue-to-soap-summary
|
25 |
+
- keivalya/MedQuad-MedicalQnADataset
|
26 |
+
- ruslanmv/ai-medical-dataset
|
27 |
+
- Shekswess/medical_llama3_instruct_dataset_short
|
28 |
+
- ShenRuililin/MedicalQnA
|
29 |
+
- virattt/financial-qa-10K
|
30 |
+
- PatronusAI/financebench
|
31 |
+
- takala/financial_phrasebank
|
32 |
+
- Replete-AI/code_bagel
|
33 |
+
- athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW
|
34 |
+
- IlyaGusev/gpt_roleplay_realm
|
35 |
+
- rickRossie/bluemoon_roleplay_chat_data_300k_messages
|
36 |
+
- jtatman/hypnosis_dataset
|
37 |
+
- Hypersniper/philosophy_dialogue
|
38 |
+
- Locutusque/function-calling-chatml
|
39 |
+
- bible-nlp/biblenlp-corpus
|
40 |
+
- DatadudeDev/Bible
|
41 |
+
- Helsinki-NLP/bible_para
|
42 |
+
- HausaNLP/AfriSenti-Twitter
|
43 |
+
- aixsatoshi/Chat-with-cosmopedia
|
44 |
+
- xz56/react-llama
|
45 |
+
- BeIR/hotpotqa
|
46 |
+
- YBXL/medical_book_train_filtered
|
47 |
+
- SkunkworksAI/reasoning-0.01
|
48 |
+
- THUDM/LongWriter-6k
|
49 |
+
- WhiteRabbitNeo/WRN-Chapter-1
|
50 |
+
- WhiteRabbitNeo/Code-Functions-Level-Cyber
|
51 |
+
- WhiteRabbitNeo/Code-Functions-Level-General
|
52 |
+
language:
|
53 |
+
- en
|
54 |
+
- sw
|
55 |
+
- ig
|
56 |
+
- so
|
57 |
+
- es
|
58 |
+
- ca
|
59 |
+
- xh
|
60 |
+
- zu
|
61 |
+
- ha
|
62 |
+
- tw
|
63 |
+
- af
|
64 |
+
- hi
|
65 |
+
- bm
|
66 |
+
- su
|
67 |
+
library_name: transformers
|
68 |
+
tags:
|
69 |
+
- llama-cpp
|
70 |
+
- gguf-my-repo
|
71 |
+
---
|
72 |
+
|
73 |
+
# LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned-Q4_K_M-GGUF
|
74 |
+
This model was converted to GGUF format from [`LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned`](https://huggingface.co/LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
75 |
+
Refer to the [original model card](https://huggingface.co/LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned) for more details on the model.
|
76 |
+
|
77 |
+
## Use with llama.cpp
|
78 |
+
Install llama.cpp through brew (works on Mac and Linux)
|
79 |
+
|
80 |
+
```bash
|
81 |
+
brew install llama.cpp
|
82 |
+
|
83 |
+
```
|
84 |
+
Invoke the llama.cpp server or the CLI.
|
85 |
+
|
86 |
+
### CLI:
|
87 |
+
```bash
|
88 |
+
llama-cli --hf-repo LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned-Q4_K_M-GGUF --hf-file _spydaz_web_ai_chatqa_react_project_ultrafinetuned-q4_k_m.gguf -p "The meaning to life and the universe is"
|
89 |
+
```
|
90 |
+
|
91 |
+
### Server:
|
92 |
+
```bash
|
93 |
+
llama-server --hf-repo LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned-Q4_K_M-GGUF --hf-file _spydaz_web_ai_chatqa_react_project_ultrafinetuned-q4_k_m.gguf -c 2048
|
94 |
+
```
|
95 |
+
|
96 |
+
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
|
97 |
+
|
98 |
+
Step 1: Clone llama.cpp from GitHub.
|
99 |
+
```
|
100 |
+
git clone https://github.com/ggerganov/llama.cpp
|
101 |
+
```
|
102 |
+
|
103 |
+
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
|
104 |
+
```
|
105 |
+
cd llama.cpp && LLAMA_CURL=1 make
|
106 |
+
```
|
107 |
+
|
108 |
+
Step 3: Run inference through the main binary.
|
109 |
+
```
|
110 |
+
./llama-cli --hf-repo LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned-Q4_K_M-GGUF --hf-file _spydaz_web_ai_chatqa_react_project_ultrafinetuned-q4_k_m.gguf -p "The meaning to life and the universe is"
|
111 |
+
```
|
112 |
+
or
|
113 |
+
```
|
114 |
+
./llama-server --hf-repo LeroyDyer/_Spydaz_Web_AI_ChatQA_ReAct_Project_UltraFineTuned-Q4_K_M-GGUF --hf-file _spydaz_web_ai_chatqa_react_project_ultrafinetuned-q4_k_m.gguf -c 2048
|
115 |
+
```
|