liuylhf commited on
Commit
3a8b34a
1 Parent(s): 817fa89

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. README.md +2 -2
  2. config.json +1 -1
  3. ggml-model-Q4_K_M.gguf +2 -2
  4. ggml-model-f16.gguf +2 -2
README.md CHANGED
@@ -8,13 +8,13 @@ tags:
8
 
9
  ## Empower Functions Model
10
 
11
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6424a49f12ba34f9894ab9b7/CH-d0WcBGT46T06ifrV-z.png)
12
 
13
  [https://github.com/empower-ai/empower-functions](https://github.com/empower-ai/empower-functions)
14
 
15
  Empower Functions is a family of LLMs(large language models) that offer GPT-4 level capabilities for real-world "tool using" use cases, with full compatibility support to be served as a drop-in replacement.
16
 
17
- This is the GGUF version of the `llama3-empower-functions-small` model, for other sizes, please visit [the empower-functions collection](https://huggingface.co/collections/empower-dev/empower-functions-663e9a22df93b46804df75a8)
18
 
19
  ## Key Features
20
  * Automatic tool using, able to decide when to use tools and when to converse, optimized for long conversations
 
8
 
9
  ## Empower Functions Model
10
 
11
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6424a49f12ba34f9894ab9b7/wXkYX_NXEFtpmBsQd6nIV.png)
12
 
13
  [https://github.com/empower-ai/empower-functions](https://github.com/empower-ai/empower-functions)
14
 
15
  Empower Functions is a family of LLMs(large language models) that offer GPT-4 level capabilities for real-world "tool using" use cases, with full compatibility support to be served as a drop-in replacement.
16
 
17
+ This is the `llama3-empower-functions-small` model, for other sizes, please visit [the empower-functions collection](https://huggingface.co/collections/empower-dev/empower-functions-663e9a22df93b46804df75a8)
18
 
19
  ## Key Features
20
  * Automatic tool using, able to decide when to use tools and when to converse, optimized for long conversations
config.json CHANGED
@@ -23,6 +23,6 @@
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.38.0",
26
- "use_cache": true,
27
  "vocab_size": 128256
28
  }
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.38.0",
26
+ "use_cache": false,
27
  "vocab_size": 128256
28
  }
ggml-model-Q4_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4b8c65f5a83ffa243e2a872aab60e8f635abc86fc8bc9ceb7497312e9ce63d1
3
- size 4920734016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29098fce09a50e21c335f82b0e96a6fd036c09a4f820094a6a4e8728b181648c
3
+ size 4920734048
ggml-model-f16.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:578ac8d2f488c97ee65ec51b195af594c2099dc7a95b819f4f327e903a3f46ac
3
- size 16068890944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58eee2e3b79796dda4550f2bf199a94dec8ac7ddfd6b039fce67f6df1708ba05
3
+ size 16068890976