prithivMLmods commited on
Commit
6387d88
·
verified ·
1 Parent(s): d4b50c0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +76 -1
README.md CHANGED
@@ -18,9 +18,84 @@ tags:
18
  - **Finetuned from model :** unsloth/llama-3.2-1b-instruct-bnb-4bit
19
 
20
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
 
23
- [Watch the demo video](Demo/gguf.mp4)
24
  ![Demo of Project](Demo/gguf.gif)
25
 
26
 
 
18
  - **Finetuned from model :** unsloth/llama-3.2-1b-instruct-bnb-4bit
19
 
20
  This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
21
+ Here’s a revised version of your instructions formatted for a GitHub `README.md` file:
22
 
23
+ ---
24
+
25
+ # Run with Ollama
26
+
27
+ ### Download and Install Ollama
28
+ To get started, download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your Windows or Mac system.
29
+
30
+ ### Run Your Own Model in Minutes
31
+
32
+ ### Steps to Run GGUF Models:
33
+
34
+ #### 1. Create the Model File
35
+ - Name your model file appropriately, for example, `metallama`.
36
+
37
+ #### 2. Add the Template Command
38
+ - Include a `FROM` line with the base model file. For instance:
39
+
40
+ ```bash
41
+ FROM Llama-3.2-1B.F16.gguf
42
+ ```
43
+
44
+ - Make sure the model file is in the same directory as your script.
45
+
46
+ #### 3. Create and Patch the Model
47
+ - Use the following command in your terminal to create and patch your model:
48
+
49
+ ```bash
50
+ ollama create metallama -f ./metallama
51
+ ```
52
+
53
+ - Upon success, a confirmation message will appear.
54
+
55
+ - To verify that the model was created successfully, run:
56
+
57
+ ```bash
58
+ ollama list
59
+ ```
60
+
61
+ Ensure that `metallama` appears in the list of models.
62
+
63
+ ---
64
+
65
+ ## Running the Model
66
+
67
+ To run the model, use:
68
+
69
+ ```bash
70
+ ollama run metallama
71
+ ```
72
+
73
+ ### Sample Usage
74
+
75
+ In the command prompt, run:
76
+
77
+ ```bash
78
+ D:\>ollama run metallama
79
+ ```
80
+
81
+ Example interaction:
82
+
83
+ ```plaintext
84
+ >>> write a mini passage about space x
85
+ Space X, the private aerospace company founded by Elon Musk, is revolutionizing the field of space exploration.
86
+ With its ambitious goals to make humanity a multi-planetary species and establish a sustainable human presence in
87
+ the cosmos, Space X has become a leading player in the industry. The company's spacecraft, like the Falcon 9, have
88
+ demonstrated remarkable capabilities, allowing for the transport of crews and cargo into space with unprecedented
89
+ efficiency. As technology continues to advance, the possibility of establishing permanent colonies on Mars becomes
90
+ increasingly feasible, thanks in part to the success of reusable rockets that can launch multiple times without
91
+ sustaining significant damage. The journey towards becoming a multi-planetary species is underway, and Space X
92
+ plays a pivotal role in pushing the boundaries of human exploration and settlement.
93
+ ```
94
+
95
+ ---
96
+
97
+ You’re now ready to run your own model with Ollama!
98
 
 
99
  ![Demo of Project](Demo/gguf.gif)
100
 
101