bala00712200502 commited on
Commit
55e7d36
·
verified ·
1 Parent(s): 417ff6e

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ # A6B - Custom Language Model
3
+
4
+ ## Model Description
5
+ - **Model Type:** A6B Custom Language Model
6
+ - **Language:** English
7
+ - **Training Data:** Custom A6B Assistant dataset
8
+ - **Developer:** Balakarthikeyan
9
+
10
+ ## Training Details
11
+ - **Number of Epochs:** 3
12
+ - **Learning Rate:** 0.0002
13
+ - **Batch Size:** 1
14
+ - **Gradient Accumulation Steps:** 16
15
+ - **Max Sequence Length:** 512
16
+
17
+ ## Usage
18
+
19
+ ```python
20
+ from transformers import AutoModelForCausalLM, AutoTokenizer
21
+
22
+ # Load model and tokenizer
23
+ model = AutoModelForCausalLM.from_pretrained("bala00712200502/A6B7B")
24
+ tokenizer = AutoTokenizer.from_pretrained("bala00712200502/A6B7B")
25
+
26
+ # Example usage
27
+ def generate_response(prompt):
28
+ inputs = tokenizer(prompt, return_tensors="pt")
29
+ outputs = model.generate(
30
+ inputs["input_ids"],
31
+ max_length=512,
32
+ temperature=0.7,
33
+ top_p=0.95,
34
+ do_sample=True
35
+ )
36
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
37
+ return response
38
+
39
+ # Example usage
40
+ response = generate_response("Hello, how can I help you?")
41
+ print(response)
42
+ ```
43
+
44
+ ## Training Infrastructure
45
+ - Trained on AMD EPYC 7V12 64-Core Processor
46
+ - Training Framework: PyTorch with 🤗 Transformers
47
+
48
+ ## License
49
+ This model is for research purposes only.
50
+
51
+ ## Developer
52
+ Created by Balakarthikeyan
adapter_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 16,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "v_proj",
29
+ "k_proj",
30
+ "o_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "trainable_token_indices": null,
34
+ "use_dora": false,
35
+ "use_rslora": false
36
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744504981f8ac823da672c48eacadc7d66fd8f64150567adfb6aaba8c6b97bd1
3
+ size 18045856
chat_template.jinja ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}
2
+ {% if message['role'] == 'user' %}
3
+ {{ '<|user|>
4
+ ' + message['content'] + eos_token }}
5
+ {% elif message['role'] == 'system' %}
6
+ {{ '<|system|>
7
+ ' + message['content'] + eos_token }}
8
+ {% elif message['role'] == 'assistant' %}
9
+ {{ '<|assistant|>
10
+ ' + message['content'] + eos_token }}
11
+ {% endif %}
12
+ {% if loop.last and add_generation_prompt %}
13
+ {{ '<|assistant|>' }}
14
+ {% endif %}
15
+ {% endfor %}
config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "A6BForCausalLM"
4
+ ],
5
+ "model_type": "a6b",
6
+ "torch_dtype": "float32",
7
+ "transformers_version": "4.37.2",
8
+ "task_specific_params": {
9
+ "chat": {
10
+ "temperature": 0.7,
11
+ "top_p": 0.95,
12
+ "do_sample": true,
13
+ "max_length": 512
14
+ }
15
+ }
16
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }