itlwas commited on
Commit
48e8652
·
verified ·
1 Parent(s): 0784bba

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ language:
4
+ - en
5
+ - de
6
+ - fr
7
+ - it
8
+ - pt
9
+ - hi
10
+ - es
11
+ - th
12
+ pipeline_tag: text-generation
13
+ tags:
14
+ - triangulum_5b
15
+ - sft
16
+ - chain_of_thought
17
+ - ollama
18
+ - text-generation-inference
19
+ - llama_for_causal_lm
20
+ - reasoning
21
+ - deep_think
22
+ - CoT
23
+ - LCoT
24
+ - llama-cpp
25
+ - gguf-my-repo
26
+ library_name: transformers
27
+ metrics:
28
+ - code_eval
29
+ - accuracy
30
+ - competition_math
31
+ - character
32
+ base_model: prithivMLmods/Triangulum-5B-it
33
+ ---
34
+
35
+ # itlwas/Triangulum-5B-it-Q4_K_M-GGUF
36
+ This model was converted to GGUF format from [`prithivMLmods/Triangulum-5B-it`](https://huggingface.co/prithivMLmods/Triangulum-5B-it) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
37
+ Refer to the [original model card](https://huggingface.co/prithivMLmods/Triangulum-5B-it) for more details on the model.
38
+
39
+ ## Use with llama.cpp
40
+ Install llama.cpp through brew (works on Mac and Linux)
41
+
42
+ ```bash
43
+ brew install llama.cpp
44
+
45
+ ```
46
+ Invoke the llama.cpp server or the CLI.
47
+
48
+ ### CLI:
49
+ ```bash
50
+ llama-cli --hf-repo itlwas/Triangulum-5B-it-Q4_K_M-GGUF --hf-file triangulum-5b-it-q4_k_m.gguf -p "The meaning to life and the universe is"
51
+ ```
52
+
53
+ ### Server:
54
+ ```bash
55
+ llama-server --hf-repo itlwas/Triangulum-5B-it-Q4_K_M-GGUF --hf-file triangulum-5b-it-q4_k_m.gguf -c 2048
56
+ ```
57
+
58
+ 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.
59
+
60
+ Step 1: Clone llama.cpp from GitHub.
61
+ ```
62
+ git clone https://github.com/ggerganov/llama.cpp
63
+ ```
64
+
65
+ 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).
66
+ ```
67
+ cd llama.cpp && LLAMA_CURL=1 make
68
+ ```
69
+
70
+ Step 3: Run inference through the main binary.
71
+ ```
72
+ ./llama-cli --hf-repo itlwas/Triangulum-5B-it-Q4_K_M-GGUF --hf-file triangulum-5b-it-q4_k_m.gguf -p "The meaning to life and the universe is"
73
+ ```
74
+ or
75
+ ```
76
+ ./llama-server --hf-repo itlwas/Triangulum-5B-it-Q4_K_M-GGUF --hf-file triangulum-5b-it-q4_k_m.gguf -c 2048
77
+ ```