ed-neo4j commited on
Commit
82706a5
·
verified ·
1 Parent(s): 2236015

Add files using upload-large-folder tool

Browse files
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Llama-3.3-70B-Instruct-bnb-4bit",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 64,
23
+ "num_hidden_layers": 80,
24
+ "num_key_value_heads": 8,
25
+ "pad_token_id": 128004,
26
+ "pretraining_tp": 1,
27
+ "quantization_config": {
28
+ "bnb_4bit_compute_dtype": "bfloat16",
29
+ "bnb_4bit_quant_type": "nf4",
30
+ "bnb_4bit_use_double_quant": true,
31
+ "llm_int8_enable_fp32_cpu_offload": false,
32
+ "llm_int8_has_fp16_weight": false,
33
+ "llm_int8_skip_modules": null,
34
+ "llm_int8_threshold": 6.0,
35
+ "load_in_4bit": true,
36
+ "load_in_8bit": false,
37
+ "quant_method": "bitsandbytes"
38
+ },
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_scaling": {
41
+ "factor": 8.0,
42
+ "high_freq_factor": 4.0,
43
+ "low_freq_factor": 1.0,
44
+ "original_max_position_embeddings": 8192,
45
+ "rope_type": "llama3"
46
+ },
47
+ "rope_theta": 500000.0,
48
+ "tie_word_embeddings": false,
49
+ "torch_dtype": "bfloat16",
50
+ "transformers_version": "4.48.3",
51
+ "unsloth_fixed": true,
52
+ "unsloth_version": "2025.2.4",
53
+ "use_cache": true,
54
+ "vocab_size": 128256
55
+ }
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": "4.48.3"
14
+ }
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da9b94df179e7da3e336d028a9d5a353c4a9bd5cc7e03da5c918b9970b3fd85
3
+ size 4949082241
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ddb600b83b0c76b836a433009166b4f4dce92e826dae914a0b5e6ef78a4b343
3
+ size 4977054863
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e4eec0e9755aad5113f79d9d3c5d0c752064776ff07927b4d6f329b0330613
3
+ size 4977088008
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a26455c829e5392bd6473cb42dd00dc89ab0816a4bc58a620cabdb62f5b2efde
3
+ size 4933786769
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8dcd7941e75fbc75344bd82c0641f2eb406aa03c36ed5cb012cd6b7b0bc4298
3
+ size 4977055044
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8fe62b898a4b33b15caa1b5ddfa9bbcc567034b731c081821567e49ac96f062
3
+ size 4977055019
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3080a9f85d8f93621a2241146cfbe946e8fef18c66b1ba74e226f6ee684623b
3
+ size 4977088003
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:108e50592a8138494f8481fb47c04718ae1fbc4924035c2fc9b88b621d439bf6
3
+ size 4750027551
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -2060,7 +2060,7 @@
2060
  ],
2061
  "model_max_length": 131072,
2062
  "pad_token": "<|finetune_right_pad_id|>",
2063
- "padding_side": "right",
2064
  "tokenizer_class": "PreTrainedTokenizerFast",
2065
  "unk_token": null
2066
  }
 
2060
  ],
2061
  "model_max_length": 131072,
2062
  "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "left",
2064
  "tokenizer_class": "PreTrainedTokenizerFast",
2065
  "unk_token": null
2066
  }