jianguozhang
commited on
Commit
•
f382700
1
Parent(s):
a7e0ed4
Add release date to xLAM model series
Browse files
README.md
CHANGED
@@ -35,10 +35,15 @@ We use [llama.cpp](https://github.com/ggerganov/llama.cpp) framework to convert
|
|
35 |
|
36 |
We provide a series of xLAMs in different sizes to cater to various applications, including those optimized for function-calling and general agent applications:
|
37 |
|
38 |
-
| Model | # Total Params | Context Length | Download Model | Download GGUF files |
|
39 |
-
|
40 |
-
| xLAM-
|
41 |
-
| xLAM-
|
|
|
|
|
|
|
|
|
|
|
42 |
|
43 |
The `fc` series of models are optimized for function-calling capability, providing fast, accurate, and structured responses based on input queries and available APIs. These models are fine-tuned based on the [deepseek-coder](https://huggingface.co/collections/deepseek-ai/deepseek-coder-65f295d7d8a0a29fe39b4ec4) models and are designed to be small enough for deployment on personal devices like phones or computers.
|
44 |
|
|
|
35 |
|
36 |
We provide a series of xLAMs in different sizes to cater to various applications, including those optimized for function-calling and general agent applications:
|
37 |
|
38 |
+
| Model | # Total Params | Context Length |Release Date | Category | Download Model | Download GGUF files |
|
39 |
+
|------------------------|----------------|----------------|----|----|----------------|----------|
|
40 |
+
| xLAM-7b-r | 7.24B | 32k | Sep. 5, 2024|General, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/xLAM-7b-r) | -- |
|
41 |
+
| xLAM-8x7b-r | 46.7B | 32k | Sep. 5, 2024|General, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/xLAM-8x7b-r) | -- |
|
42 |
+
| xLAM-8x22b-r | 141B | 64k | Sep. 5, 2024|General, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/xLAM-8x22b-r) | -- |
|
43 |
+
| xLAM-1b-fc-r | 1.35B | 16k | July 17, 2024 | Function-calling| [🤗 Link](https://huggingface.co/Salesforce/xLAM-1b-fc-r) | [🤗 Link](https://huggingface.co/Salesforce/xLAM-1b-fc-r-gguf) |
|
44 |
+
| xLAM-7b-fc-r | 6.91B | 4k | July 17, 2024| Function-calling| [🤗 Link](https://huggingface.co/Salesforce/xLAM-7b-fc-r) | [🤗 Link](https://huggingface.co/Salesforce/xLAM-7b-fc-r-gguf) |
|
45 |
+
| xLAM-v0.1-r | 46.7B | 32k | Mar. 18, 2024 |General, Function-calling | [🤗 Link](https://huggingface.co/Salesforce/xLAM-v0.1-r) | -- |
|
46 |
+
|
47 |
|
48 |
The `fc` series of models are optimized for function-calling capability, providing fast, accurate, and structured responses based on input queries and available APIs. These models are fine-tuned based on the [deepseek-coder](https://huggingface.co/collections/deepseek-ai/deepseek-coder-65f295d7d8a0a29fe39b4ec4) models and are designed to be small enough for deployment on personal devices like phones or computers.
|
49 |
|