Upload folder using huggingface_hub (#2)

- fc3f33f33f0f4ae2f1ae622ab5a4d4c1166e720852c96462db2dce7787c0fd26 (6adcac14f27494be185f489fa686bd764d610f8d)
- 98952edc8cf30f9c96d381b5b61f24fb9190e0f47c244bb4e96d19598a1593ab (18cd3fa5f45575e7593ef235efa716d69411042f)
- 45eeb925d078937066917344591444d4fb0dcde346ad6d0be4f1e34accb7ff17 (508e946e36fcc3b3bbbdc4b71c56c89a00d2e19d)
- dec405f932eec7e6036e57f041b4a88ba3cda0244e754dca51fdcb2255dc87c2 (8d715e2171b9a34ca1da27f525b1f3fb11147319)
- 06fe651bd435bf521fa9618051d54e6e29bd8a36f74c0fd951a68dc2fd6d959e (4416c9a53548f8765c6c49f9bd7f2938e4d46553)
- 6b06906991d1dce99c0708ec68cb94f6eec8e7346da89c2d2f858eef730a00c6 (9e6b9b337e228cd7fd33276fdd8c6f8794b925c0)
- 7dca25b6922f057efd86eabd5148e99220d454aab70b94f4fc492255110d0f65 (622207d02cfe7dcf3f582171620a1f0246dfabf9)
- 240e00fba4fd8880658b0e7e2b0857580907d4a9b5033b4e658e4734e728f00b (f84746946edea75a73f60efce29641ccf231fdb5)
- ef2e6451544498cc8029638c407b0bef6c2c3b7827ff99e4ff8724f42d29982c (1c17239f03c204e8d9720dd80de2e1a804653413)
- af901daa122c8438a4cd71b59b127d9b5a008ef03ca9d08d1b0bf1059ba78e10 (31d4812feade68c1c06a16fcee87444e5a06a5d3)
- 99ebe2f9eca6273423bc41eed75122b4460746d2bea32e0746ec0ec7a6d5d274 (b62d445225d012d46054297f99b16cc65f43fa27)
- a512dee76dfea181109a8bf63c51ac83f0ed6ce2de419345c2cfc7c89369f7bc (511e7e5808bb48b1e87d37c3be9f4f672bd043de)
- Delete .ipynb_checkpoints (61bd86eb52a998563dce9bbceeff6dc3d9d6b7ba)
- 1.1 examples (880c754c89c92751a9642394a14ddb5e5a425970)


Co-authored-by: scott <[email protected]>

README.md

@@ -23,17 +23,20 @@ license: apache-2.0
 
 Fireplace-13b is a function calling model built on the Llama 2 architecture.
   - Built on llama-2-13b architecture, using [CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) as the base model.
-  - Emphasizes function calling and code-instruct as skills. 
+  - Emphasizes function calling and code-instruct as skills.
+  - Version 1.1 improves output structure for a superior user experience.
 
 (If you're looking for a friendly general-purpose chat model, try ours: [llama-13b](https://huggingface.co/ValiantLabs/ShiningValiantXS) and [70b](https://huggingface.co/ValiantLabs/ShiningValiant))
 
 ## Version
 
-This is Version **1.0** of Fireplace-13b. 
+This is Version **1.1** of Fireplace-13b. 
 
 The current version of Fireplace-13b uses [CodeLlama-13b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf) trained on [glaive-function-calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2).
 
-Fireplace is the first release in our Build Tools campaign, to deliver helpful open source capabilities for users and creators. We're excitedly working on our next open source models now!
+Fireplace is the first release in our Build Tools campaign, to deliver helpful open source capabilities for users and creators.
+
+**The next release in our Build Tools series will be coming soon, with an initial release at 70b parameters** - we're very excited to bring this to everyone!
 
 We're also working to bring Fireplace to larger model architectures, to maximize baseline model capability and function-calling performance.
 
@@ -42,25 +45,29 @@ Fireplace-13b specializes in function calling and code instruct/chat.
 
 See [CodeLlama-13b-Instruct-hf](codellama/CodeLlama-13b-Instruct-hf) for code capabilities of the base model.
 
-For function calling in this version of the model, the recommended format is taken from [the training dataset](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2). Assistant can make function calls, which are given between \<functioncall> and <|endoftext|>: 
+For function calling in this version of the model, the recommended format is to deliver the function(s) in a system message and then proceed with chat:
 
+SYSTEM: You are Fireplace, an expert code assistant with access to the following functions. Use them if required -
+{
+    ""name"": ""function_name"",
+}
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/WTX8qlnXXw2PQ9t6OI1VB.png)
+USER: Can you (do thing from function)?
 
+ASSISTANT: 
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/oJGb5hpUTy1KPxIdaIG5F.png)
+Assistant will deliver function call responses between \<functioncall> and <|endoftext|>: 
 
 
-(Please note that <|endoftext|> is not an EOS/EOT token, it is used to indicate the end of an 'ASSISTANT: ' response in the training data. Post-processing should be used to extract the function response as required by the user.)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/rpfkQKAS0E3483Qxn1HIF.png)
 
-For handling of function call responses, append "FUNCTION RESPONSE: " to the existing chat history:
 
+(Please note that <|endoftext|> is not an EOS/EOT token, it is used to indicate the end of function call responses specifically.)
 
-
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/6D0KnhAZPDUOZOJM_btTn.png)
+For handling of function call responses, append "FUNCTION RESPONSE: " to the existing chat history:
 
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/Ruwdx_hxGmFdedzQ7d-ZJ.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/2bKX9Zsk6pHJxKYqEprcq.png)
 
 
 Fireplace is optimized for function/code capabilities and not general chat, but it has also been trained to utilize general instruct-chat capabilities:

config.json

@@ -22,7 +22,7 @@
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 32016
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.36.2"
+  "transformers_version": "4.37.2"
 }

model-00001-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ec70b6f8ab4a6a7b458961023af957beb19a676648076b1bd07ba956f3a201
+oid sha256:9261ecc9bf641f8194d9dfd707a1c627e1646d086b54bf1e5368cc8c860b3812
 size 4881575536

model-00002-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3678b125d5f3077a4dce0ae3c760e26bff2c830ce340e530fa6551779d8434
+oid sha256:0df40517f03d482f5a2d6473c6af305003672cea8feaae5d1288d84d93a25ac7
 size 4970418112

model-00003-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd086d24373a1e419b90b72d0c43b1a70005cbcdf8ccb9c0a980429ab78ab2b
+oid sha256:559377e2227c601d98c925cdfa40cfe812ec8ce3e23fada0a95fcc469f4947a3
 size 4970418120

model-00004-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e76854902ea1c22feb4c06971da01dd8f0ccec119a3877aec0b93f86f651c1
+oid sha256:37a4ec442035d5413c07b6c6119c9cb4c778134f3c72c98f49f9a4d2006116b4
 size 4970418144

model-00005-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0a4becfaf4d3d729b75a2aa6fc8ed6104c6e7921a81a1f81f99907fea18b04
+oid sha256:fa47ed211ebb221bd983c5b1b94880016733081095dfece70f27bbfad24a4d23
 size 4970418144

model-00006-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7583391979299ea23498a3152b92a241b16fdc97945724643eceb29925552688
+oid sha256:1e99052645564812a6f1b0b83aab13dee1b69055fd595b0fd08b4daec507059d
 size 4792119040

model-00007-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4fb9b67ee3c2cc9c54317c0a350d15d3847b6aa659d917d06009f45f2d9a318
+oid sha256:3e7b3d7c1b78eb105bf733b5aa01f08e266ff238ed8e1571a8341ddc1a7c4d9b
 size 4792160232

model-00008-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4515966c8ac9f3b587921df80c57df71f75fa7bfbfea6120a11625f6929fde
+oid sha256:d9f3e00e10671dd8992efc35587e10d400e27659cc05db98b75e3483c47b7dd6
 size 4792160224

model-00009-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404ac08869a828501d24a7459ec622be1f13407418e03eeedb472e917f9c2224
+oid sha256:8152175b1f95a51b56ac83961600a07a67bd1a527bb4c44b7b12842efe4c4947
 size 4970418144

model-00010-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dcd06c9714464f8766ab89912f87868c4a01844cc26a82c1f8116ac2824ce65
+oid sha256:a9e752b04a0bf5606dd72922f197610ff1af8bef01a1f6726062d1a5df49c8fc
 size 4970418144

model-00011-of-00011.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9878c5bff699108585b0466e188ef60d9f886c862cfe24f1dd31941be84710
+oid sha256:6de442a4ca387c6cd1efa09072a849a4fc841d05b06d26d62fca4fbaa90699f3
 size 2983630864

tokenizer_config.json

@@ -77,7 +77,7 @@
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
   "suffix_token": "▁<SUF>",
-  "tokenizer_class": "LlamaTokenizer",
+  "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }