pcuenq HF staff commited on
Commit
b3e8c27
·
1 Parent(s): 2bc3933

Clarify HF format, model table by @philschmid (#2)

Browse files

- Clarify HF format, model table by

@philschmid
(0b362120fab8babae93624b1d6c7eaccaa2707a2)

Files changed (1) hide show
  1. README.md +6 -15
README.md CHANGED
@@ -9,7 +9,7 @@ pinned: false
9
 
10
  # 🦙 Code Llama
11
 
12
- This organization is the home of the Code Llama models.
13
  Code Llama is a code-specialized version of Llama 2 that was created by further training Llama 2 on its code-specific datasets, sampling more data from that same dataset for longer.
14
  Essentially, Code Llama features enhanced coding capabilities.
15
  It can generate code and natural language about code, from both code and natural language prompts (e.g., “Write me a function that outputs the fibonacci sequence”).
@@ -18,20 +18,11 @@ It supports many of the most popular programming languages used today, including
18
 
19
  There are three sizes (7b, 13b, 34b) as well as three flavours (base model, Python fine-tuned, and instruction tuned).
20
 
21
- ## Base models
22
- - [CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf)
23
- - [CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf)
24
- - [CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf)
25
-
26
- ## Python models
27
- - [CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)
28
- - [CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf)
29
- - [CodeLlama-34b-Ptyhon-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf)
30
-
31
- ## Instruction models models
32
- - [CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf)
33
- - [CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf)
34
- - [CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf)
35
 
36
  ## Demo
37
 
 
9
 
10
  # 🦙 Code Llama
11
 
12
+ This organization is the home of the Code Llama models in the Hugging Face Transformers format.
13
  Code Llama is a code-specialized version of Llama 2 that was created by further training Llama 2 on its code-specific datasets, sampling more data from that same dataset for longer.
14
  Essentially, Code Llama features enhanced coding capabilities.
15
  It can generate code and natural language about code, from both code and natural language prompts (e.g., “Write me a function that outputs the fibonacci sequence”).
 
18
 
19
  There are three sizes (7b, 13b, 34b) as well as three flavours (base model, Python fine-tuned, and instruction tuned).
20
 
21
+ | | Base Model | Python | Instruct |
22
+ | --- | ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
23
+ | 7B | [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf) | [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
24
+ | 13B | [codellama/CodeLlama-13b-hf](https://huggingface.co/codellama/CodeLlama-13b-hf) | [codellama/CodeLlama-13b-Python-hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf) | [codellama/CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
25
+ | 34B | [codellama/CodeLlama-34b-hf](https://huggingface.co/codellama/CodeLlama-34b-hf) | [codellama/CodeLlama-34b-Python-hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf) | [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) |
 
 
 
 
 
 
 
 
 
26
 
27
  ## Demo
28