Training in progress, step 100
Browse files- README.md +58 -6
- adapter_config.json +8 -5
- adapter_model.safetensors +1 -1
- chat_template.jinja +93 -0
- special_tokens_map.json +1 -2
- tokenizer_config.json +1 -4
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,58 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
4 |
-
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Llama-3.2-1B-Instruct
|
3 |
+
library_name: transformers
|
4 |
+
model_name: Llama-3.2-1B-finetuned
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
- sft
|
8 |
+
- trl
|
9 |
+
licence: license
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Card for Llama-3.2-1B-finetuned
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
|
15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
+
|
17 |
+
## Quick start
|
18 |
+
|
19 |
+
```python
|
20 |
+
from transformers import pipeline
|
21 |
+
|
22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
23 |
+
generator = pipeline("text-generation", model="stuser2023/Llama-3.2-1B-finetuned", device="cuda")
|
24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
25 |
+
print(output["generated_text"])
|
26 |
+
```
|
27 |
+
|
28 |
+
## Training procedure
|
29 |
+
|
30 |
+
|
31 |
+
|
32 |
+
|
33 |
+
This model was trained with SFT.
|
34 |
+
|
35 |
+
### Framework versions
|
36 |
+
|
37 |
+
- TRL: 0.21.0
|
38 |
+
- Transformers: 4.55.2
|
39 |
+
- Pytorch: 2.6.0+cu124
|
40 |
+
- Datasets: 4.0.0
|
41 |
+
- Tokenizers: 0.21.4
|
42 |
+
|
43 |
+
## Citations
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
Cite TRL as:
|
48 |
+
|
49 |
+
```bibtex
|
50 |
+
@misc{vonwerra2022trl,
|
51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
53 |
+
year = 2020,
|
54 |
+
journal = {GitHub repository},
|
55 |
+
publisher = {GitHub},
|
56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
57 |
+
}
|
58 |
+
```
|
adapter_config.json
CHANGED
@@ -20,20 +20,23 @@
|
|
20 |
"megatron_core": "megatron.core",
|
21 |
"modules_to_save": null,
|
22 |
"peft_type": "LORA",
|
|
|
23 |
"r": 8,
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
-
"
|
28 |
-
"q_proj",
|
29 |
-
"k_proj",
|
30 |
"up_proj",
|
|
|
31 |
"gate_proj",
|
32 |
-
"
|
33 |
-
"v_proj"
|
|
|
34 |
],
|
|
|
35 |
"task_type": "CAUSAL_LM",
|
36 |
"trainable_token_indices": null,
|
37 |
"use_dora": false,
|
|
|
38 |
"use_rslora": false
|
39 |
}
|
|
|
20 |
"megatron_core": "megatron.core",
|
21 |
"modules_to_save": null,
|
22 |
"peft_type": "LORA",
|
23 |
+
"qalora_group_size": 16,
|
24 |
"r": 8,
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
+
"down_proj",
|
|
|
|
|
29 |
"up_proj",
|
30 |
+
"q_proj",
|
31 |
"gate_proj",
|
32 |
+
"k_proj",
|
33 |
+
"v_proj",
|
34 |
+
"o_proj"
|
35 |
],
|
36 |
+
"target_parameters": null,
|
37 |
"task_type": "CAUSAL_LM",
|
38 |
"trainable_token_indices": null,
|
39 |
"use_dora": false,
|
40 |
+
"use_qalora": false,
|
41 |
"use_rslora": false
|
42 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22573704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48c19c43ae43ef5f6b7b76546e349ee174aedffe81ed1241a7996222bdc5718d
|
3 |
size 22573704
|
chat_template.jinja
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{{- bos_token }}
|
2 |
+
{%- if custom_tools is defined %}
|
3 |
+
{%- set tools = custom_tools %}
|
4 |
+
{%- endif %}
|
5 |
+
{%- if not tools_in_user_message is defined %}
|
6 |
+
{%- set tools_in_user_message = true %}
|
7 |
+
{%- endif %}
|
8 |
+
{%- if not date_string is defined %}
|
9 |
+
{%- if strftime_now is defined %}
|
10 |
+
{%- set date_string = strftime_now("%d %b %Y") %}
|
11 |
+
{%- else %}
|
12 |
+
{%- set date_string = "26 Jul 2024" %}
|
13 |
+
{%- endif %}
|
14 |
+
{%- endif %}
|
15 |
+
{%- if not tools is defined %}
|
16 |
+
{%- set tools = none %}
|
17 |
+
{%- endif %}
|
18 |
+
|
19 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
20 |
+
{%- if messages[0]['role'] == 'system' %}
|
21 |
+
{%- set system_message = messages[0]['content']|trim %}
|
22 |
+
{%- set messages = messages[1:] %}
|
23 |
+
{%- else %}
|
24 |
+
{%- set system_message = "" %}
|
25 |
+
{%- endif %}
|
26 |
+
|
27 |
+
{#- System message #}
|
28 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
29 |
+
{%- if tools is not none %}
|
30 |
+
{{- "Environment: ipython\n" }}
|
31 |
+
{%- endif %}
|
32 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
33 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
34 |
+
{%- if tools is not none and not tools_in_user_message %}
|
35 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
36 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
37 |
+
{{- "Do not use variables.\n\n" }}
|
38 |
+
{%- for t in tools %}
|
39 |
+
{{- t | tojson(indent=4) }}
|
40 |
+
{{- "\n\n" }}
|
41 |
+
{%- endfor %}
|
42 |
+
{%- endif %}
|
43 |
+
{{- system_message }}
|
44 |
+
{{- "<|eot_id|>" }}
|
45 |
+
|
46 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
47 |
+
{%- if tools_in_user_message and not tools is none %}
|
48 |
+
{#- Extract the first user message so we can plug it in here #}
|
49 |
+
{%- if messages | length != 0 %}
|
50 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
51 |
+
{%- set messages = messages[1:] %}
|
52 |
+
{%- else %}
|
53 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
54 |
+
{%- endif %}
|
55 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
56 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
57 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
58 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
59 |
+
{{- "Do not use variables.\n\n" }}
|
60 |
+
{%- for t in tools %}
|
61 |
+
{{- t | tojson(indent=4) }}
|
62 |
+
{{- "\n\n" }}
|
63 |
+
{%- endfor %}
|
64 |
+
{{- first_user_message + "<|eot_id|>"}}
|
65 |
+
{%- endif %}
|
66 |
+
|
67 |
+
{%- for message in messages %}
|
68 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
69 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
70 |
+
{%- elif 'tool_calls' in message %}
|
71 |
+
{%- if not message.tool_calls|length == 1 %}
|
72 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
73 |
+
{%- endif %}
|
74 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
76 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
77 |
+
{{- '"parameters": ' }}
|
78 |
+
{{- tool_call.arguments | tojson }}
|
79 |
+
{{- "}" }}
|
80 |
+
{{- "<|eot_id|>" }}
|
81 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
82 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
83 |
+
{%- if message.content is mapping or message.content is iterable %}
|
84 |
+
{{- message.content | tojson }}
|
85 |
+
{%- else %}
|
86 |
+
{{- message.content }}
|
87 |
+
{%- endif %}
|
88 |
+
{{- "<|eot_id|>" }}
|
89 |
+
{%- endif %}
|
90 |
+
{%- endfor %}
|
91 |
+
{%- if add_generation_prompt %}
|
92 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
93 |
+
{%- endif %}
|
special_tokens_map.json
CHANGED
@@ -12,6 +12,5 @@
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
-
}
|
16 |
-
"pad_token": "<|eot_id|>"
|
17 |
}
|
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
+
}
|
|
|
16 |
}
|
tokenizer_config.json
CHANGED
@@ -2050,7 +2050,6 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
@@ -2059,7 +2058,5 @@
|
|
2059 |
"attention_mask"
|
2060 |
],
|
2061 |
"model_max_length": 131072,
|
2062 |
-
"
|
2063 |
-
"padding": true,
|
2064 |
-
"tokenizer_class": "PreTrainedTokenizer"
|
2065 |
}
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|eot_id|>",
|
2055 |
"extra_special_tokens": {},
|
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 131072,
|
2061 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
2062 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:faacb9f8697e8de4b0eeebb670b1eaead4e3e9a1923415514d8820f3b291764f
|
3 |
+
size 5688
|