Danielrahmai1991 commited on
Commit
d6c8827
1 Parent(s): 6614908

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json CHANGED
@@ -1,20 +1,23 @@
1
  {
2
- "_name_or_path": "jondurbin/bagel-7b-v0.5",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
  "hidden_act": "silu",
10
  "hidden_size": 4096,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
 
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
  "num_key_value_heads": 8,
 
18
  "quantization_config": {
19
  "bnb_4bit_compute_dtype": "float16",
20
  "bnb_4bit_quant_type": "nf4",
@@ -28,12 +31,12 @@
28
  "quant_method": "bitsandbytes"
29
  },
30
  "rms_norm_eps": 1e-05,
31
- "rope_theta": 1000000.0,
32
- "sliding_window": null,
33
  "tie_word_embeddings": false,
34
  "torch_dtype": "float16",
35
- "transformers_version": "4.41.2",
36
- "unsloth_version": "2024.6",
37
- "use_cache": false,
38
- "vocab_size": 32000
39
  }
 
1
  {
2
+ "_name_or_path": "unsloth/llama-3-8b-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": 128001,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
  "num_attention_heads": 32,
18
  "num_hidden_layers": 32,
19
  "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
  "quantization_config": {
22
  "bnb_4bit_compute_dtype": "float16",
23
  "bnb_4bit_quant_type": "nf4",
 
31
  "quant_method": "bitsandbytes"
32
  },
33
  "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 500000.0,
36
  "tie_word_embeddings": false,
37
  "torch_dtype": "float16",
38
+ "transformers_version": "4.42.3",
39
+ "unsloth_version": "2024.7",
40
+ "use_cache": true,
41
+ "vocab_size": 128256
42
  }
generation_config.json CHANGED
@@ -1,6 +1,9 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.41.2"
 
 
 
6
  }
 
1
  {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.42.3"
9
  }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eefa26b42b32e7d9ba3983219057bc1ad3c801ad0f1237c939a944284815686
3
+ size 4652072879
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
3
+ size 1050673280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff