cddelgado commited on
Commit
0942139
1 Parent(s): 4a1a1db

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +60 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ tags:
6
+ - llama-cpp
7
+ - gguf-my-repo
8
+ base_model: alpindale/Mistral-7B-v0.2-hf
9
+ datasets:
10
+ - cognitivecomputations/dolphin
11
+ - cognitivecomputations/dolphin-coder
12
+ - cognitivecomputations/samantha-data
13
+ - jondurbin/airoboros-2.2.1
14
+ - teknium/openhermes-2.5
15
+ - m-a-p/Code-Feedback
16
+ - m-a-p/CodeFeedback-Filtered-Instruction
17
+ model-index:
18
+ - name: dolphin-2.8-mistral-7b-v02
19
+ results:
20
+ - task:
21
+ type: text-generation
22
+ dataset:
23
+ name: HumanEval
24
+ type: openai_humaneval
25
+ metrics:
26
+ - type: pass@1
27
+ value: 0.469
28
+ name: pass@1
29
+ verified: false
30
+ ---
31
+
32
+ # cddelgado/dolphin-2.8-mistral-7b-v02-Q5_K_M-GGUF
33
+ This model was converted to GGUF format from [`cognitivecomputations/dolphin-2.8-mistral-7b-v02`](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02) 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/cognitivecomputations/dolphin-2.8-mistral-7b-v02) for more details on the model.
35
+ ## Use with llama.cpp
36
+
37
+ Install llama.cpp through brew.
38
+
39
+ ```bash
40
+ brew install ggerganov/ggerganov/llama.cpp
41
+ ```
42
+ Invoke the llama.cpp server or the CLI.
43
+
44
+ CLI:
45
+
46
+ ```bash
47
+ llama-cli --hf-repo cddelgado/dolphin-2.8-mistral-7b-v02-Q5_K_M-GGUF --model dolphin-2.8-mistral-7b-v02.Q5_K_M.gguf -p "The meaning to life and the universe is"
48
+ ```
49
+
50
+ Server:
51
+
52
+ ```bash
53
+ llama-server --hf-repo cddelgado/dolphin-2.8-mistral-7b-v02-Q5_K_M-GGUF --model dolphin-2.8-mistral-7b-v02.Q5_K_M.gguf -c 2048
54
+ ```
55
+
56
+ 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.
57
+
58
+ ```
59
+ git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m dolphin-2.8-mistral-7b-v02.Q5_K_M.gguf -n 128
60
+ ```