Igorrr0 commited on
Commit
26b4528
·
verified ·
1 Parent(s): 6008a20

Upload 3 files

Browse files
Files changed (3) hide show
  1. chat_template.jinja +17 -0
  2. config.json +50 -0
  3. generation_config.json +14 -0
chat_template.jinja ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% if 'role' in messages[0] %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
2
+
3
+ ' + message['content'] | trim + '<|eot_id|>' }}{% elif message['role'] == 'assistant' %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' + message['content'] | trim + '<|eot_id|>' }}{% else %}{{ '<|start_header_id|>' + message['role'] + '<|end_header_id|>
6
+
7
+ ' + message['content'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
8
+
9
+ ' }}{% endif %}{% else %}{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{ '<|start_header_id|>user<|end_header_id|>
10
+
11
+ ' + message['value'] | trim + '<|eot_id|>' }}{% elif message['from'] == 'gpt' %}{{ '<|start_header_id|>assistant<|end_header_id|>
12
+
13
+ ' + message['value'] | trim + '<|eot_id|>' }}{% else %}{{ '<|start_header_id|>' + message['from'] + '<|end_header_id|>
14
+
15
+ ' + message['value'] | trim + '<|eot_id|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
16
+
17
+ ' }}{% endif %}{% endif %}
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "float16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 24,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128004,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "bnb_4bit_compute_dtype": "float16",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": {
37
+ "factor": 32.0,
38
+ "high_freq_factor": 4.0,
39
+ "low_freq_factor": 1.0,
40
+ "original_max_position_embeddings": 8192,
41
+ "rope_type": "llama3"
42
+ },
43
+ "rope_theta": 500000.0,
44
+ "tie_word_embeddings": true,
45
+ "transformers_version": "4.57.1",
46
+ "unsloth_fixed": true,
47
+ "unsloth_version": "2025.11.3",
48
+ "use_cache": true,
49
+ "vocab_size": 128256
50
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "max_length": 131072,
10
+ "pad_token_id": 128004,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.57.1"
14
+ }