jahyungu commited on
Commit
579a402
·
verified ·
1 Parent(s): 4d18536

Training in progress, epoch 1

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|system|>\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- set remaining_messages = messages[1:] %}
6
+ {%- else %}
7
+ {%- set remaining_messages = messages %}
8
+ {%- endif %}
9
+ {{- 'You are a Falcon assistant skilled in function calling. You are helpful, respectful, and concise.\n\n# Tools\n\nYou have access to the following functions. You MUST use them to answer questions when needed. For each function call, you MUST return a JSON object inside <tool_call></tool_call> tags.\n\n<tools>' + tools|tojson(indent=2) + '</tools>\n\n# Output Format\n\nYour response MUST follow this format when making function calls:\n<tool_call>\n[\n {"name": "function_name", "arguments": {"arg1": "value1", "arg2": "value2"}},\n {"name": "another_function", "arguments": {"arg": "value"}}\n]\n</tool_call>\nIf no function calls are needed, respond normally without the tool_call tags.\n' }}
10
+ {%- for message in remaining_messages %}
11
+ {%- if message['role'] == 'user' %}
12
+ {{- '<|user|>\n' + message['content'] + '\n' }}
13
+ {%- elif message['role'] == 'assistant' %}
14
+ {%- if message.content %}
15
+ {{- '<|assistant|>\n' + message['content'] }}
16
+ {%- endif %}
17
+ {%- if message.tool_calls %}
18
+ {{- '\n<tool_call>\n' }}
19
+ {{- message.tool_calls|tojson(indent=2) }}
20
+ {{- '\n</tool_call>' }}
21
+ {%- endif %}
22
+ {{- eos_token + '\n' }}
23
+ {%- elif message['role'] == 'tool' %}
24
+ {{- '<|assistant|>\n<tool_response>\n' + message['content'] + '\n</tool_response>\n' }}
25
+ {%- endif %}
26
+ {%- endfor %}
27
+ {{- '<|assistant|>\n' if add_generation_prompt }}
28
+ {%- else %}
29
+ {%- for message in messages %}
30
+ {%- if message['role'] == 'system' %}
31
+ {{- '<|system|>\n' + message['content'] + '\n' }}
32
+ {%- elif message['role'] == 'user' %}
33
+ {{- '<|user|>\n' + message['content'] + '\n' }}
34
+ {%- elif message['role'] == 'assistant' %}
35
+ {%- if not loop.last %}
36
+ {{- '<|assistant|>\n' + message['content'] + eos_token + '\n' }}
37
+ {%- else %}
38
+ {{- '<|assistant|>\n' + message['content'] + eos_token }}
39
+ {%- endif %}
40
+ {%- endif %}
41
+ {%- if loop.last and add_generation_prompt %}
42
+ {{- '<|assistant|>\n' }}
43
+ {%- endif %}
44
+ {%- endfor %}
45
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 11,
9
+ "head_dim": 256,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 18,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 2023,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 1000042,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.55.0",
28
+ "use_cache": true,
29
+ "vocab_size": 131072
30
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fecc6a554cd7ae488ddccbddd5432a7ce9cbbb041384169b37c7985f687d1690
3
+ size 3338836632
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>EMAIL_ADDRESS<<",
12
+ ">>IP_ADDRESS<<",
13
+ "<|startoftext|>",
14
+ ">>IP_ADDRESS_0<<",
15
+ ">>IP_ADDRESS_1<<",
16
+ ">>IP_ADDRESS_2<<",
17
+ ">>IP_ADDRESS_3<<",
18
+ ">>IP_ADDRESS_4<<",
19
+ ">>IP_ADDRESS_5<<",
20
+ ">>IP_ADDRESS_6<<",
21
+ ">>IP_ADDRESS_7<<",
22
+ ">>IP_ADDRESS_8<<",
23
+ ">>IP_ADDRESS_9<<",
24
+ ">>PASSWORD<<",
25
+ ">>KEY<<"
26
+ ],
27
+ "eos_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<|pad|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfd42cac2892bc34c42a08700449883b614c8e503c9098bc89070d7ba1c7a159
3
+ size 5432