Hugging Face's logo

qualcomm
/
Phi-3.5-mini-instruct

Text Generation
PyTorch
llm
generative_ai
android
Model card Files Community
qaihm-bot commited on
Commit
b529f53
·
verified ·
1 Parent(s): bd665b0

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +6 -7
README.md CHANGED
@@ -1,10 +1,9 @@
1
  ---
2
  library_name: pytorch
3
- license: mit
4
  tags:
5
  - llm
6
  - generative_ai
7
- - quantized
8
  - android
9
  pipeline_tag: text-generation
10
 
@@ -25,7 +24,7 @@ This model is an implementation of Phi-3.5-mini-instruct found [here](https://hu
25
 
26
  ### Model Details
27
 
28
- - **Model Type:** Text generation
29
  - **Model Stats:**
30
  - Input sequence length for Prompt Processor: 128
31
  - Context length: 4096
@@ -41,11 +40,11 @@ This model is an implementation of Phi-3.5-mini-instruct found [here](https://hu
41
  - TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
42
  - Response Rate: Rate of response generation after the first response token.
43
 
44
- | Model | Device | Chipset | Target Runtime | Response Rate (tokens per second) | Time To First Token (range, seconds)
45
  |---|---|---|---|---|---|
46
- | Phi-3.5-mini-instruct | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 13.01 | 0.1469056 - 4.7009792 | -- | [Phi-3.5-mini-instruct.bin](https://huggingface.co/qualcomm/Phi-3.5-mini-instruct/blob/main/Phi-3.5-mini-instruct.bin) |
47
- | Phi-3.5-mini-instruct | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.2 | 0.185833 - 5.946656 | -- | Use Export Script |
48
- | Phi-3.5-mini-instruct | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 14.73 | 0.1195948 - 3.8270336 | -- | Use Export Script |
49
 
50
  ## Deploying Phi-3.5-mini-instruct on-device
51
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - llm
6
  - generative_ai
 
7
  - android
8
  pipeline_tag: text-generation
9
 
 
24
 
25
  ### Model Details
26
 
27
+ - **Model Type:** Model_use_case.text_generation
28
  - **Model Stats:**
29
  - Input sequence length for Prompt Processor: 128
30
  - Context length: 4096
 
40
  - TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
41
  - Response Rate: Rate of response generation after the first response token.
42
 
43
+ | Model | Precision | Device | Chipset | Target Runtime | Response Rate (tokens per second) | Time To First Token (range, seconds)
44
  |---|---|---|---|---|---|
45
+ | Phi-3.5-Mini-Instruct | w4a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 13.01 | 0.1469056 - 4.7009792 | -- | Use Export Script |
46
+ | Phi-3.5-Mini-Instruct | w4a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.2 | 0.185833 - 5.946656 | -- | Use Export Script |
47
+ | Phi-3.5-Mini-Instruct | w4a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 14.73 | 0.1195948 - 3.8270336 | -- | Use Export Script |
48
 
49
  ## Deploying Phi-3.5-mini-instruct on-device
50