danielhanchen commited on
Commit
70d37f6
·
verified ·
1 Parent(s): bce4d67

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -7,6 +7,7 @@
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128001,
 
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
@@ -28,7 +29,12 @@
28
  "bnb_4bit_use_double_quant": true,
29
  "llm_int8_enable_fp32_cpu_offload": false,
30
  "llm_int8_has_fp16_weight": false,
31
- "llm_int8_skip_modules": null,
 
 
 
 
 
32
  "llm_int8_threshold": 6.0,
33
  "load_in_4bit": true,
34
  "load_in_8bit": false,
@@ -45,8 +51,8 @@
45
  "rope_theta": 500000.0,
46
  "tie_word_embeddings": false,
47
  "torch_dtype": "bfloat16",
48
- "transformers_version": "4.44.2",
49
- "unsloth_version": "2024.9",
50
  "use_cache": true,
51
  "vocab_size": 128256
52
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/meta-Llama-3.1-8B",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
  "eos_token_id": 128001,
10
+ "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 4096,
13
  "initializer_range": 0.02,
 
29
  "bnb_4bit_use_double_quant": true,
30
  "llm_int8_enable_fp32_cpu_offload": false,
31
  "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": [
33
+ "lm_head",
34
+ "multi_modal_projector",
35
+ "merger",
36
+ "modality_projection"
37
+ ],
38
  "llm_int8_threshold": 6.0,
39
  "load_in_4bit": true,
40
  "load_in_8bit": false,
 
51
  "rope_theta": 500000.0,
52
  "tie_word_embeddings": false,
53
  "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.49.0.dev0",
55
+ "unsloth_fixed": true,
56
  "use_cache": true,
57
  "vocab_size": 128256
58
  }
generation_config.json CHANGED
@@ -7,5 +7,5 @@
7
  "pad_token_id": 128004,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
- "transformers_version": "4.44.2"
11
  }
 
7
  "pad_token_id": 128004,
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
+ "transformers_version": "4.49.0.dev0"
11
  }
special_tokens_map.json CHANGED
@@ -13,5 +13,11 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|finetune_right_pad_id|>"
 
 
 
 
 
 
17
  }
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "added_tokens_decoder": {
3
  "128000": {
4
  "content": "<|begin_of_text|>",
@@ -2052,6 +2053,7 @@
2052
  "bos_token": "<|begin_of_text|>",
2053
  "clean_up_tokenization_spaces": true,
2054
  "eos_token": "<|end_of_text|>",
 
2055
  "model_input_names": [
2056
  "input_ids",
2057
  "attention_mask"
@@ -2059,5 +2061,6 @@
2059
  "model_max_length": 131072,
2060
  "pad_token": "<|finetune_right_pad_id|>",
2061
  "padding_side": "left",
2062
- "tokenizer_class": "PreTrainedTokenizerFast"
 
2063
  }
 
1
  {
2
+ "add_bos_token": true,
3
  "added_tokens_decoder": {
4
  "128000": {
5
  "content": "<|begin_of_text|>",
 
2053
  "bos_token": "<|begin_of_text|>",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|end_of_text|>",
2056
+ "extra_special_tokens": {},
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"
 
2061
  "model_max_length": 131072,
2062
  "pad_token": "<|finetune_right_pad_id|>",
2063
  "padding_side": "left",
2064
+ "tokenizer_class": "PreTrainedTokenizer",
2065
+ "unk_token": null
2066
  }