Triangle104 commited on
Commit
16b64b0
1 Parent(s): 832f9ce

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +74 -0
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - PrimeIntellect/fineweb-edu
5
+ - PrimeIntellect/fineweb
6
+ - PrimeIntellect/StackV1-popular
7
+ - mlfoundations/dclm-baseline-1.0-parquet
8
+ - open-web-math/open-web-math
9
+ - arcee-ai/EvolKit-75K
10
+ - arcee-ai/Llama-405B-Logits
11
+ - arcee-ai/The-Tomb
12
+ - mlabonne/open-perfectblend-fixed
13
+ - microsoft/orca-agentinstruct-1M-v1-cleaned
14
+ - Post-training-Data-Flywheel/AutoIF-instruct-61k-with-funcs
15
+ - Team-ACE/ToolACE
16
+ - Synthia-coder
17
+ - ServiceNow-AI/M2Lingual
18
+ - AI-MO/NuminaMath-TIR
19
+ - allenai/tulu-3-sft-personas-code
20
+ - allenai/tulu-3-sft-personas-math
21
+ - allenai/tulu-3-sft-personas-math-grade
22
+ - allenai/tulu-3-sft-personas-algebra
23
+ language:
24
+ - en
25
+ base_model: PrimeIntellect/INTELLECT-1-Instruct
26
+ pipeline_tag: text-generation
27
+ tags:
28
+ - llama-cpp
29
+ - gguf-my-repo
30
+ ---
31
+
32
+ # Triangle104/INTELLECT-1-Instruct-Q5_K_M-GGUF
33
+ This model was converted to GGUF format from [`PrimeIntellect/INTELLECT-1-Instruct`](https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
34
+ Refer to the [original model card](https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct) for more details on the model.
35
+
36
+ ## Use with llama.cpp
37
+ Install llama.cpp through brew (works on Mac and Linux)
38
+
39
+ ```bash
40
+ brew install llama.cpp
41
+
42
+ ```
43
+ Invoke the llama.cpp server or the CLI.
44
+
45
+ ### CLI:
46
+ ```bash
47
+ llama-cli --hf-repo Triangle104/INTELLECT-1-Instruct-Q5_K_M-GGUF --hf-file intellect-1-instruct-q5_k_m.gguf -p "The meaning to life and the universe is"
48
+ ```
49
+
50
+ ### Server:
51
+ ```bash
52
+ llama-server --hf-repo Triangle104/INTELLECT-1-Instruct-Q5_K_M-GGUF --hf-file intellect-1-instruct-q5_k_m.gguf -c 2048
53
+ ```
54
+
55
+ 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.
56
+
57
+ Step 1: Clone llama.cpp from GitHub.
58
+ ```
59
+ git clone https://github.com/ggerganov/llama.cpp
60
+ ```
61
+
62
+ 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).
63
+ ```
64
+ cd llama.cpp && LLAMA_CURL=1 make
65
+ ```
66
+
67
+ Step 3: Run inference through the main binary.
68
+ ```
69
+ ./llama-cli --hf-repo Triangle104/INTELLECT-1-Instruct-Q5_K_M-GGUF --hf-file intellect-1-instruct-q5_k_m.gguf -p "The meaning to life and the universe is"
70
+ ```
71
+ or
72
+ ```
73
+ ./llama-server --hf-repo Triangle104/INTELLECT-1-Instruct-Q5_K_M-GGUF --hf-file intellect-1-instruct-q5_k_m.gguf -c 2048
74
+ ```