ehristoforu commited on
Commit
d595941
·
verified ·
1 Parent(s): 164012c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ library_name: transformers
4
+ tags:
5
+ - fluently-lm
6
+ - fluently
7
+ - prinum
8
+ - instruct
9
+ - trained
10
+ - math
11
+ - roleplay
12
+ - reasoning
13
+ - axolotl
14
+ - unsloth
15
+ - argilla
16
+ - qwen2
17
+ - llama-cpp
18
+ - gguf-my-repo
19
+ license: mit
20
+ language:
21
+ - en
22
+ - fr
23
+ - es
24
+ - ru
25
+ - zh
26
+ - ja
27
+ - fa
28
+ - code
29
+ datasets:
30
+ - fluently-sets/ultraset
31
+ - fluently-sets/ultrathink
32
+ - fluently-sets/reasoning-1-1k
33
+ - fluently-sets/MATH-500-Overall
34
+ pipeline_tag: text-generation
35
+ base_model: fluently-lm/FluentlyLM-Prinum
36
+ ---
37
+
38
+ # ehristoforu/FluentlyLM-Prinum-Q2_K-GGUF
39
+ This model was converted to GGUF format from [`fluently-lm/FluentlyLM-Prinum`](https://huggingface.co/fluently-lm/FluentlyLM-Prinum) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
40
+ Refer to the [original model card](https://huggingface.co/fluently-lm/FluentlyLM-Prinum) for more details on the model.
41
+
42
+ ## Use with llama.cpp
43
+ Install llama.cpp through brew (works on Mac and Linux)
44
+
45
+ ```bash
46
+ brew install llama.cpp
47
+
48
+ ```
49
+ Invoke the llama.cpp server or the CLI.
50
+
51
+ ### CLI:
52
+ ```bash
53
+ llama-cli --hf-repo ehristoforu/FluentlyLM-Prinum-Q2_K-GGUF --hf-file fluentlylm-prinum-q2_k.gguf -p "The meaning to life and the universe is"
54
+ ```
55
+
56
+ ### Server:
57
+ ```bash
58
+ llama-server --hf-repo ehristoforu/FluentlyLM-Prinum-Q2_K-GGUF --hf-file fluentlylm-prinum-q2_k.gguf -c 2048
59
+ ```
60
+
61
+ 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.
62
+
63
+ Step 1: Clone llama.cpp from GitHub.
64
+ ```
65
+ git clone https://github.com/ggerganov/llama.cpp
66
+ ```
67
+
68
+ 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).
69
+ ```
70
+ cd llama.cpp && LLAMA_CURL=1 make
71
+ ```
72
+
73
+ Step 3: Run inference through the main binary.
74
+ ```
75
+ ./llama-cli --hf-repo ehristoforu/FluentlyLM-Prinum-Q2_K-GGUF --hf-file fluentlylm-prinum-q2_k.gguf -p "The meaning to life and the universe is"
76
+ ```
77
+ or
78
+ ```
79
+ ./llama-server --hf-repo ehristoforu/FluentlyLM-Prinum-Q2_K-GGUF --hf-file fluentlylm-prinum-q2_k.gguf -c 2048
80
+ ```