bychwa commited on
Commit
e36f019
·
verified ·
1 Parent(s): a40c0ef

Training in progress, step 500

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ model_name: kitchenbot-chat
4
+ tags:
5
+ - generated_from_trainer
6
+ - trl
7
+ - sft
8
+ licence: license
9
+ ---
10
+
11
+ # Model Card for kitchenbot-chat
12
+
13
+ This model is a fine-tuned version of [None](https://huggingface.co/None).
14
+ It has been trained using [TRL](https://github.com/huggingface/trl).
15
+
16
+ ## Quick start
17
+
18
+ ```python
19
+ from transformers import pipeline
20
+
21
+ 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?"
22
+ generator = pipeline("text-generation", model="bychwa/kitchenbot-chat", device="cuda")
23
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
24
+ print(output["generated_text"])
25
+ ```
26
+
27
+ ## Training procedure
28
+
29
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/bychwa-bouer-tech/kitchenbot/runs/syrnpr69)
30
+
31
+
32
+
33
+ This model was trained with SFT.
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 1.9.2
38
+ - Transformers: 5.14.1
39
+ - Pytorch: 2.5.1+cu121
40
+ - Datasets: 5.0.1
41
+ - Tokenizers: 0.22.2
42
+
43
+ ## Citations
44
+
45
+
46
+
47
+ Cite TRL as:
48
+
49
+ ```bibtex
50
+ @software{vonwerra2020trl,
51
+ title = {{TRL: Transformers Reinforcement Learning}},
52
+ author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
53
+ license = {Apache-2.0},
54
+ url = {https://github.com/huggingface/trl},
55
+ year = {2020}
56
+ }
57
+ ```
adapter_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "models/kitchenbot-base",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": true,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 32,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "monteclora_config": null,
27
+ "peft_type": "LORA",
28
+ "peft_version": "0.20.0",
29
+ "qalora_group_size": 16,
30
+ "r": 16,
31
+ "rank_pattern": {},
32
+ "revision": null,
33
+ "target_modules": [
34
+ "c_proj",
35
+ "c_attn"
36
+ ],
37
+ "target_parameters": null,
38
+ "task_type": "CAUSAL_LM",
39
+ "trainable_token_indices": null,
40
+ "use_bdlora": null,
41
+ "use_dora": false,
42
+ "use_qalora": false,
43
+ "use_rslora": false,
44
+ "velora_config": null
45
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882e5c1059de588d3f2fc3cec6b540a8239a6b74f0c6b2f28327bd7c0e8a85d3
3
+ size 1085872
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'user' %}<|user|>
2
+ {{ message['content'] }}
3
+ {% elif message['role'] == 'assistant' %}<|assistant|>
4
+ {{ message['content'] }}{{ eos_token }}
5
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>
6
+ {% endif %}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|bos|>",
4
+ "eos_token": "<|eos|>",
5
+ "extra_special_tokens": [
6
+ "<|user|>",
7
+ "<|assistant|>"
8
+ ],
9
+ "is_local": true,
10
+ "local_files_only": false,
11
+ "max_length": 256,
12
+ "model_max_length": 1000000000000000019884624838656,
13
+ "pad_token": "<|pad|>",
14
+ "stride": 0,
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "truncation_side": "right",
17
+ "truncation_strategy": "longest_first",
18
+ "unk_token": "<|unk|>"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d3cfd7cb13fa139512e6bea215ce8ea1fb8b6a99297c7ae7be66fb6d9e1121
3
+ size 5368