RonanMcGovern commited on
Commit
39c4036
1 Parent(s): d06f7b2

update for launch of mistral 7b function calling

Browse files
Files changed (1) hide show
  1. README.md +11 -8
README.md CHANGED
@@ -12,22 +12,25 @@ tags:
12
  - functions
13
  - function calling
14
  - sharded
15
- - gguf
16
- - gptq
17
  ---
18
- # Function Calling Llama 2 (version 2)
19
  - Function calling Llama extends the hugging face Llama 2 models with function calling capabilities.
20
  - The model responds with a structured json argument with the function name and arguments.
21
 
 
 
 
 
22
  **Improvements with v2**
23
  1. Shortened syntax: Only function descriptions are needed for inference and no added instruction is required.
24
  2. Function descriptions are moved outside of the system prompt. This avoids the behaviour of function calling being affected by how the system prompt had been trained to influence the model.
25
 
26
  Available models:
27
- - Llama-7B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-adapters-v2)), ([GGUF - files are in this main branch]) - Free
28
- - Llama-13B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here: €19.99 per user/seat.](https://buy.stripe.com/9AQ7te3lHdmbdZ68wz)
29
- - CodeLlama-34B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-adapters-v2)) - Paid, [purchase here: €44.99 per user/seat.](https://buy.stripe.com/cN27teg8t2Hx5sA8wM)
30
- - Llama-70B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here: €99 per user/seat.](https://buy.stripe.com/8wMdRC1dzci75sA4gy)
 
31
 
32
  ## Performance and Tips
33
 
@@ -41,7 +44,7 @@ Check out this video overview of performance [here](https://www.loom.com/share/8
41
 
42
  Llama-7B with function calling is licensed according to the Meta Community license.
43
 
44
- Llama-13B, Code-llama-34b and Llama-70B with function calling require the purchase of access.
45
  - Commercial license purchase required per user.
46
  - Licenses are not transferable to other users/entities.
47
 
 
12
  - functions
13
  - function calling
14
  - sharded
 
 
15
  ---
16
+ # Function Calling Llama 2 + Mistral Models (version 2)
17
  - Function calling Llama extends the hugging face Llama 2 models with function calling capabilities.
18
  - The model responds with a structured json argument with the function name and arguments.
19
 
20
+ **Recent Updates**
21
+ - October 11th 2023 -> added Mistral 7B with function calling
22
+ - October 11th 2023 -> new models pushed, trained on an improved underlying dataset
23
+
24
  **Improvements with v2**
25
  1. Shortened syntax: Only function descriptions are needed for inference and no added instruction is required.
26
  2. Function descriptions are moved outside of the system prompt. This avoids the behaviour of function calling being affected by how the system prompt had been trained to influence the model.
27
 
28
  Available models:
29
+ - Llama-7B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-adapters-v2)), ([GGUF - files are in the main branch of the base model]) - Free
30
+ - Mistral-7B-Instruct-v0.1 with function calling ([Base Model](https://huggingface.co/Trelis/Mistral-7B-Instruct-v0.1-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Mistral-7B-Instruct-v0.1-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/cN2cNybSdgyncV25kQ)
31
+ - Llama-13B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-13b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/9AQ7te3lHdmbdZ68wz)
32
+ - CodeLlama-34B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/CodeLlama-34b-Instruct-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/cN27teg8t2Hx5sA8wM)
33
+ - Llama-70B-chat with function calling ([Base Model](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/Llama-2-70b-chat-hf-function-calling-adapters-v2)) - Paid, [purchase here](https://buy.stripe.com/8wMdRC1dzci75sA4gy)
34
 
35
  ## Performance and Tips
36
 
 
44
 
45
  Llama-7B with function calling is licensed according to the Meta Community license.
46
 
47
+ Mistral-7B, Llama-13B, Code-llama-34b, Llama-70B and Falcon-180B with function calling require the purchase of access.
48
  - Commercial license purchase required per user.
49
  - Licenses are not transferable to other users/entities.
50