v0.2 (#2)

- v0.2 (aefbfb1277bc08ec1f2166b03c0659eea6d6bae1)
- Update README.md (a9df87be4af1c824c0a4d245ad25a1c9e16f65ff)

README.md

@@ -25,6 +25,11 @@ This model was developed by StarfleetAI with the aim of it being used for autono
 
 ## Current Features
 
+### `v0.2`
+
+- Improved function calling in long conversations
+- Function call arguments became a JSON string to comply with OpenAI
+
 ### `v0.1.1`
 
 - Function call response role changed to `tool` to comply with OpenAI
@@ -36,7 +41,6 @@ This model was developed by StarfleetAI with the aim of it being used for autono
 
 ## Work To Do
 
-- Needs more training on examples where function call should be performed in the middle/end parts of the conversation, rather than in the beginning
 - Needs to eliminate some hallucinations (it, for example, sometimes regressing news articles instead of calling the `get_rss_feed` function, and stuff like that)
 - Correct typography (`Answer: 123` instead of `Answer:123`)
 - Current date / time / timezone conversational abilities ("Schedule a call tomorrow at 6PM")
@@ -91,7 +95,7 @@ For now, the model is only capable of calling one function at a time.
 ### Example Function Call
 
 ```
-<|fn_start|>{"name": "generate_password", "arguments": {"length": 42}}<|fn_end|>
+<|fn_start|>{"name": "generate_password", "arguments": "{\"length\": 42}"}<|fn_end|>
 ```
 
 ## Function Call Response
@@ -125,7 +129,7 @@ You are a helpful assistant.<|im_end|>
 <|im_start|>user
 Generate a password, 42 characters long<|im_end|>
 <|im_start|>assistant
-<|fn_start|>{"name": "generate_password", "arguments": {"length": 42}}<|fn_end|><|im_end|>
+<|fn_start|>{"name": "generate_password", "arguments": "{\"length\": 42}"}<|fn_end|><|im_end|>
 <|im_start|>tool
 {"result": "87cc47fbc865a290d7c7de4be3c893175c51a566b3"}<|im_end|>
 <|im_start|>assistant

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "tmp",
+  "_name_or_path": "Open-Orca/Mistral-7B-OpenOrca",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -21,7 +21,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.37.1",
+  "transformers_version": "4.37.2",
   "use_cache": false,
   "vocab_size": 32004
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 32000,
-  "transformers_version": "4.37.1"
+  "transformers_version": "4.37.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62b9c4420579e8d5e3abf60fdc1ca6419635a3b6dd4803a604d30e7ab81bd9f
+oid sha256:4a71c46c3c9b876e87b7ec005305429b4844927c6b87e4a0a28bd6bd2dbcabdc
 size 4943195104

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15daa90388d1d69e1684485d74318921f137e41ea84da33c8ee1e1e97b27fb20
+oid sha256:3f9e597c27d779f38d2ee6d892d97ed07cef304c81da2a28be1d7cbd8d893f82
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428319eb10fa9972caec1e4260e5611ef0837be0583e17954d0643f579acf517
+oid sha256:b083d0b31291502ce1e6bba235fd2d64e727a09d06e2402fe184214ab4139a0e
 size 4540549112

special_tokens_map.json

@@ -38,9 +38,9 @@
   },
   "unk_token": {
     "content": "<unk>",
-    "lstrip": false,
+    "lstrip": true,
     "normalized": false,
-    "rstrip": false,
+    "rstrip": true,
     "single_word": false
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2ebcd8264c606488d96b46aeca3b4382bbdaf5f3d0ccc74d7c360b2f4f4cfd9
+oid sha256:fd4454f7fb0dfa8edc606f22d8d19c5395b34b860407a59e62bcd405072b23e7
 size 4664