RonanMcGovern commited on
Commit
ad8a331
·
1 Parent(s): 431233b

add zephyr

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -13,11 +13,12 @@ tags:
13
  - function calling
14
  - sharded
15
  ---
16
- # Function Calling Llama 2 + Mistral + Deepseek Coder 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
  - November 6th 2023 -> added Deepseek Coder 1.3B, 6.7B and 33B
22
  - October 11th 2023 -> added Mistral 7B with function calling
23
  - October 11th 2023 -> new models pushed, trained on an improved underlying dataset
@@ -29,6 +30,7 @@ tags:
29
  Most Popular Models:
30
  - Deepseek-Coder-1.3B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/deepseek-coder-1.3b-instruct-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/deepseek-coder-1.3b-instruct-function-calling-adapters-v2/settings)) - Paid, [purchase here](https://buy.stripe.com/9AQbJubSda9Z8EM00A)
31
  - 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
 
32
  - 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)
33
  - Deepseek-Coder-6.7B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/deepseek-coder-6.7b-instruct-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/deepseek-coder-6.7b-instruct-function-calling-adapters-v2/settings)) - Paid, [purchase here](https://buy.stripe.com/cN27te5tPa9Z6wEdRo)
34
  - Deepseek-Coder-33B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/deepseek-coder-33b-instruct-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/deepseek-coder-33b-instruct-function-calling-adapters-v2/settings)) - Paid, [purchase here](https://buy.stripe.com/9AQ6pabSd81RcV25kT)
@@ -56,6 +58,8 @@ Mistral-7B, Llama-13B, Code-llama-34b, Llama-70B and Falcon-180B with function c
56
 
57
  Use of all Llama models with function calling is further subject to terms in the [Meta license](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).
58
 
 
 
59
  ## Dataset
60
 
61
  The dataset used for training this model can be found at [Trelis Function Calling Extended Dataset](https://huggingface.co/datasets/Trelis/function_calling_extended).
 
13
  - function calling
14
  - sharded
15
  ---
16
+ # Function Calling Llama 2 + Mistral + Zephyr + Deepseek Coder 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
+ - Nov 8th 2023 -> added Zephyr beta, an improved version of Mistral 7B (achieved via DPO)
22
  - November 6th 2023 -> added Deepseek Coder 1.3B, 6.7B and 33B
23
  - October 11th 2023 -> added Mistral 7B with function calling
24
  - October 11th 2023 -> new models pushed, trained on an improved underlying dataset
 
30
  Most Popular Models:
31
  - Deepseek-Coder-1.3B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/deepseek-coder-1.3b-instruct-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/deepseek-coder-1.3b-instruct-function-calling-adapters-v2/settings)) - Paid, [purchase here](https://buy.stripe.com/9AQbJubSda9Z8EM00A)
32
  - 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
33
+ - zephyr-7b-beta with function calling ([Base Model](https://huggingface.co/Trelis/zephyr-7b-beta-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/zephyr-7b-beta-function-calling-adapters-v2)), ([GGUF - files are in the main branch of the base model]) - Paid, [purchase here](https://buy.stripe.com/14k00M4pLeqf9IQbJk)
34
  - 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)
35
  - Deepseek-Coder-6.7B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/deepseek-coder-6.7b-instruct-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/deepseek-coder-6.7b-instruct-function-calling-adapters-v2/settings)) - Paid, [purchase here](https://buy.stripe.com/cN27te5tPa9Z6wEdRo)
36
  - Deepseek-Coder-33B-Instruct with function calling ([Base Model](https://huggingface.co/Trelis/deepseek-coder-33b-instruct-function-calling-v2)), ([PEFT Adapters](https://huggingface.co/Trelis/deepseek-coder-33b-instruct-function-calling-adapters-v2/settings)) - Paid, [purchase here](https://buy.stripe.com/9AQ6pabSd81RcV25kT)
 
58
 
59
  Use of all Llama models with function calling is further subject to terms in the [Meta license](https://ai.meta.com/resources/models-and-libraries/llama-downloads/).
60
 
61
+ Zephr models were generated using Ultrachat, which relies on openai. OpenAI does not permit the use of it's models to train competitive models. This makes it unclear as to whether Zephyr may be used commercial. Buyers/users do so at their sole risk.
62
+
63
  ## Dataset
64
 
65
  The dataset used for training this model can be found at [Trelis Function Calling Extended Dataset](https://huggingface.co/datasets/Trelis/function_calling_extended).