Hugging Face's logo

ysn-rfd
/
HelpingAI2.5-2B-GGUF

Text Generation
Transformers
GGUF
English
HelpingAI
Emotionally-Intelligent
EQ-focused
Conversational
SLM
llama-cpp
gguf-my-repo
conversational
Model card Files
xet
 Community
ysn-rfd commited on
Commit
c438394
·
verified ·
1 Parent(s): 4202e89

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +41 -22
README.md CHANGED
@@ -14,30 +14,49 @@ tags:
14
  - Conversational
15
  - SLM
16
  - llama-cpp
17
- - matrixportal
18
  ---
19
 
20
  # ysn-rfd/HelpingAI2.5-2B-GGUF
21
- This model was converted to GGUF format from [`HelpingAI/HelpingAI2.5-2B`](https://huggingface.co/HelpingAI/HelpingAI2.5-2B) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space.
22
  Refer to the [original model card](https://huggingface.co/HelpingAI/HelpingAI2.5-2B) for more details on the model.
23
 
24
- ## ✅ Quantized Models Download List
25
- **✨ Recommended for CPU:** `Q4_K_M` | **⚡ Recommended for ARM CPU:** `Q4_0` | **🏆 Best Quality:** `Q8_0`
26
-
27
- | 🚀 Download | 🔢 Type | 📝 Notes |
28
- |:---------|:-----|:------|
29
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q2_k.gguf) | ![Q2_K](https://img.shields.io/badge/Q2_K-1A73E8) | Basic quantization |
30
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q3_k_s.gguf) | ![Q3_K_S](https://img.shields.io/badge/Q3_K_S-34A853) | Small size |
31
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q3_k_m.gguf) | ![Q3_K_M](https://img.shields.io/badge/Q3_K_M-FBBC05) | Balanced quality |
32
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q3_k_l.gguf) | ![Q3_K_L](https://img.shields.io/badge/Q3_K_L-4285F4) | Better quality |
33
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q4_0.gguf) | ![Q4_0](https://img.shields.io/badge/Q4_0-EA4335) | Fast on ARM |
34
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q4_k_s.gguf) | ![Q4_K_S](https://img.shields.io/badge/Q4_K_S-673AB7) | Fast, recommended |
35
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q4_k_m.gguf) | ![Q4_K_M](https://img.shields.io/badge/Q4_K_M-673AB7) ⭐ | Best balance |
36
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q5_0.gguf) | ![Q5_0](https://img.shields.io/badge/Q5_0-FF6D01) | Good quality |
37
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q5_k_s.gguf) | ![Q5_K_S](https://img.shields.io/badge/Q5_K_S-0F9D58) | Balanced |
38
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q5_k_m.gguf) | ![Q5_K_M](https://img.shields.io/badge/Q5_K_M-0F9D58) | High quality |
39
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q6_k.gguf) | ![Q6_K](https://img.shields.io/badge/Q6_K-4285F4) 🏆 | Very good quality |
40
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-q8_0.gguf) | ![Q8_0](https://img.shields.io/badge/Q8_0-EA4335) ⚡ | Fast, best quality |
41
- | [Download](https://huggingface.co/ysn-rfd/HelpingAI2.5-2B-GGUF/resolve/main/helpingai2.5-2b-f16.gguf) | ![F16](https://img.shields.io/badge/F16-000000) | Maximum accuracy |
42
-
43
- 💡 **Tip:** Use `F16` for maximum precision when quality is critical
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  - Conversational
15
  - SLM
16
  - llama-cpp
17
+ - gguf-my-repo
18
  ---
19
 
20
  # ysn-rfd/HelpingAI2.5-2B-GGUF
21
+ This model was converted to GGUF format from [`HelpingAI/HelpingAI2.5-2B`](https://huggingface.co/HelpingAI/HelpingAI2.5-2B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
22
  Refer to the [original model card](https://huggingface.co/HelpingAI/HelpingAI2.5-2B) for more details on the model.
23
 
24
+ ## Use with llama.cpp
25
+ Install llama.cpp through brew (works on Mac and Linux)
26
+
27
+ ```bash
28
+ brew install llama.cpp
29
+
30
+ ```
31
+ Invoke the llama.cpp server or the CLI.
32
+
33
+ ### CLI:
34
+ ```bash
35
+ llama-cli --hf-repo ysn-rfd/HelpingAI2.5-2B-GGUF --hf-file helpingai2.5-2b-q4_0.gguf -p "The meaning to life and the universe is"
36
+ ```
37
+
38
+ ### Server:
39
+ ```bash
40
+ llama-server --hf-repo ysn-rfd/HelpingAI2.5-2B-GGUF --hf-file helpingai2.5-2b-q4_0.gguf -c 2048
41
+ ```
42
+
43
+ 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.
44
+
45
+ Step 1: Clone llama.cpp from GitHub.
46
+ ```
47
+ git clone https://github.com/ggerganov/llama.cpp
48
+ ```
49
+
50
+ 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).
51
+ ```
52
+ cd llama.cpp && LLAMA_CURL=1 make
53
+ ```
54
+
55
+ Step 3: Run inference through the main binary.
56
+ ```
57
+ ./llama-cli --hf-repo ysn-rfd/HelpingAI2.5-2B-GGUF --hf-file helpingai2.5-2b-q4_0.gguf -p "The meaning to life and the universe is"
58
+ ```
59
+ or
60
+ ```
61
+ ./llama-server --hf-repo ysn-rfd/HelpingAI2.5-2B-GGUF --hf-file helpingai2.5-2b-q4_0.gguf -c 2048
62
+ ```