add model files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,98 @@
+---
+library_name: transformers
+datasets:
+- hypervariance/function-calling-sharegpt
+---
+
+# Model Card for Model ID
+
+Gemma 2B function calling. [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) finetuned on [hypervariance/function-calling-sharegpt](https://huggingface.co/datasets/hypervariance/function-calling-sharegpt).
+
+## Usage
+
+Make sure you have the [peft](https://huggingface.co/docs/peft/en/index) package installed. You can install it with `pip install peft`.
+
+
+```python
+from transformers import AutoModelForCausalLM , AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("bodhicitta/gemma-2b-function-call", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("bodhicitta/gemma-2b-function-call", trust_remote_code=True, device_map="auto")
+
+inputs = tokenizer(prompt,return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs,do_sample=True,temperature=0.1,top_p=0.95,max_new_tokens=100)
+
+print(tokenizer.decode(outputs[0]))
+```
+
+You can also use sharegpt formatted prompts:
+
+```python
+from transformers import AutoModelForCausalLM , AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("bodhicitta/gemma-2b-function-call", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("bodhicitta/gemma-2b-function-call", trust_remote_code=True, device_map="auto")
+
+chat = [
+  {
+      "from": "system",
+      "value": "SYSTEM PROMPT",
+  },
+  {
+      "from": "human",
+      "value": "USER QUESTION"
+  },
+]
+
+prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs,do_sample=True,temperature=0.1,top_p=0.95,max_new_tokens=100)
+
+print(tokenizer.decode(outputs[0]))
+```
+
+## Prompt template
+
+```text
+You are a helpful assistant with access to the following functions. Use them if required -
+{
+    "name": "function name",
+    "description": "function description",
+    "parameters": {
+        "type": "type (object/number/string)",
+        "properties": {
+            "property_1": {
+                "type": "type",
+                "description": "property description"
+            }
+        },
+        "required": [
+            "property_1"
+        ]
+    }
+}
+
+To use these functions respond with:
+<functioncall> {"name": "function_name", "arguments": {"arg_1": "value_1", "arg_1": "value_1", ...}} </functioncall>
+
+Edge cases you must handle:
+ - If there are no functions that match the user request, you will respond politely that you cannot help.
+
+User Question:
+USER_QUESTION
+```
+
+Function calls are enclosed in `<functioncall>` `</functioncall>`.
+
+The model was trained using the same delimiters as [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it):
+
+```text
+<bos><start_of_turn>user
+Write a hello world program<end_of_turn>
+<start_of_turn>model
+```
+
+Use `<end_of_turn>` stop sequence to prevent the model from generating further text.

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.1"
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% for message in messages %}{% if message['from'] == 'system' %}{{ '<start_of_turn>user\\n' + message['value'] }}{% elif message['from'] == 'human' %}{% if loop.index0 == 1 %}{{ '\\nUser Question:\\n' }}{% else %}{{ '<start_of_turn>user\\n' }}{% endif %}{{ message['value'] + '<end_of_turn>' }}{% elif message['from'] == 'gpt' %}{{ '<start_of_turn>model\\n'  + message['value'] + ' ' + '<end_of_turn>' }}{% elif message['from'] == 'function_response' %}{{ '<start_of_turn>user\\n'  + message['value'] + ' ' + '<end_of_turn>' }}{% endif %}{% if not loop.last %}{{ '\\n' }}{% endif %}{% endfor %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% if add_generation_prompt %}{{ '\\n<start_of_turn>model\\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}