fuzzy-mittenz commited on
Commit
58893bb
·
verified ·
1 Parent(s): 68f69a6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -1
README.md CHANGED
@@ -17,9 +17,45 @@ language:
17
 
18
  ![die_Walkure-totheVictor.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/LbKT8JHfHNRUw8CN3-Wga.png)
19
 
20
- This model was converted to GGUF format from [`deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) using Importance matrics Quantization using llama.cp
21
  Refer to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) for more details on the model.
22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  ## Use with llama.cpp
24
  Install llama.cpp through brew (works on Mac and Linux)
25
 
 
17
 
18
  ![die_Walkure-totheVictor.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/LbKT8JHfHNRUw8CN3-Wga.png)
19
 
20
+ This model was converted to GGUF format from [`deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) using Importance Matrix Quantization and an inference improveing dataset updated for tool/function use using llama.cp
21
  Refer to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) for more details on the model.
22
 
23
+ ## For use with GPT4ALL
24
+ for analyzing function, system template in Jinja
25
+ ```
26
+ {{- '<|im_start|>system\n' }}
27
+ {% if toolList|length > 0 %}You have access to the following functions:
28
+ {% for tool in toolList %}
29
+ Use the function '{{tool.function}}' to: '{{tool.description}}'
30
+ {% if tool.parameters|length > 0 %}
31
+ parameters:
32
+ {% for info in tool.parameters %}
33
+ {{info.name}}:
34
+ type: {{info.type}}
35
+ description: {{info.description}}
36
+ required: {{info.required}}
37
+ {% endfor %}
38
+ {% endif %}
39
+ # Tool Instructions
40
+ If you CHOOSE to call this function ONLY reply with the following format:
41
+ '{{tool.symbolicFormat}}'
42
+ Here is an example. If the user says, '{{tool.examplePrompt}}', then you reply
43
+ '{{tool.exampleCall}}'
44
+ After the result you might reply with, '{{tool.exampleReply}}'
45
+ {% endfor %}
46
+ You MUST include both the start and end tags when you use a function.
47
+
48
+ You are a helpful AI assistant who uses the functions to break down, analyze, perform, and verify complex reasoning tasks. You SHOULD try to verify your answers using the functions where possible.
49
+ {% endif %}
50
+ {{- '<|im_end|>\n' }}
51
+ {% for message in messages %}
52
+ {{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}
53
+ {% endfor %}
54
+ {% if add_generation_prompt %}
55
+ {{ '<|im_start|>assistant\n' }}
56
+ {% endif %}
57
+ ```
58
+
59
  ## Use with llama.cpp
60
  Install llama.cpp through brew (works on Mac and Linux)
61