markhneedham commited on
Commit
a78301e
1 Parent(s): 34fd16c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +67 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: cognitivecomputations/dolphin-2.9-llama3-8b
3
+ datasets:
4
+ - cognitivecomputations/Dolphin-2.9
5
+ - teknium/OpenHermes-2.5
6
+ - m-a-p/CodeFeedback-Filtered-Instruction
7
+ - cognitivecomputations/dolphin-coder
8
+ - cognitivecomputations/samantha-data
9
+ - HuggingFaceH4/ultrachat_200k
10
+ - microsoft/orca-math-word-problems-200k
11
+ - abacusai/SystemChat-1.1
12
+ - Locutusque/function-calling-chatml
13
+ - internlm/Agent-FLAN
14
+ license: other
15
+ tags:
16
+ - generated_from_trainer
17
+ - axolotl
18
+ - llama-cpp
19
+ - gguf-my-repo
20
+ model-index:
21
+ - name: out
22
+ results: []
23
+ ---
24
+
25
+ # markhneedham/dolphin-2.9-llama3-8b-Q2_K-GGUF
26
+ This model was converted to GGUF format from [`cognitivecomputations/dolphin-2.9-llama3-8b`](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
27
+ Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b) for more details on the model.
28
+
29
+ ## Use with llama.cpp
30
+ Install llama.cpp through brew (works on Mac and Linux)
31
+
32
+ ```bash
33
+ brew install llama.cpp
34
+
35
+ ```
36
+ Invoke the llama.cpp server or the CLI.
37
+
38
+ ### CLI:
39
+ ```bash
40
+ llama-cli --hf-repo markhneedham/dolphin-2.9-llama3-8b-Q2_K-GGUF --hf-file dolphin-2.9-llama3-8b-q2_k.gguf -p "The meaning to life and the universe is"
41
+ ```
42
+
43
+ ### Server:
44
+ ```bash
45
+ llama-server --hf-repo markhneedham/dolphin-2.9-llama3-8b-Q2_K-GGUF --hf-file dolphin-2.9-llama3-8b-q2_k.gguf -c 2048
46
+ ```
47
+
48
+ 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.
49
+
50
+ Step 1: Clone llama.cpp from GitHub.
51
+ ```
52
+ git clone https://github.com/ggerganov/llama.cpp
53
+ ```
54
+
55
+ 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).
56
+ ```
57
+ cd llama.cpp && LLAMA_CURL=1 make
58
+ ```
59
+
60
+ Step 3: Run inference through the main binary.
61
+ ```
62
+ ./llama-cli --hf-repo markhneedham/dolphin-2.9-llama3-8b-Q2_K-GGUF --hf-file dolphin-2.9-llama3-8b-q2_k.gguf -p "The meaning to life and the universe is"
63
+ ```
64
+ or
65
+ ```
66
+ ./llama-server --hf-repo markhneedham/dolphin-2.9-llama3-8b-Q2_K-GGUF --hf-file dolphin-2.9-llama3-8b-q2_k.gguf -c 2048
67
+ ```