Hugging Face's logo

sca255
/
codeboxgptpython4bit

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
sft
4-bit precision
bitsandbytes
Model card Files
xet
 Community
sca255 commited on
Commit
1d3ec84
·
verified ·
1 Parent(s): 8ba770f

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show
  1. config.json +18 -19
  2. generation_config.json +4 -5
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,22 +1,24 @@
1
  {
2
- "_name_or_path": "unsloth/qwen2.5-3b-bnb-4bit",
3
  "architectures": [
4
- "Qwen2ForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151643,
9
  "hidden_act": "silu",
10
  "hidden_size": 2048,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 11008,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 36,
15
- "model_type": "qwen2",
16
- "num_attention_heads": 16,
17
- "num_hidden_layers": 36,
18
- "num_key_value_heads": 2,
19
- "pad_token_id": 151665,
 
20
  "quantization_config": {
21
  "bnb_4bit_compute_dtype": "float16",
22
  "bnb_4bit_quant_type": "nf4",
@@ -29,16 +31,13 @@
29
  "load_in_8bit": false,
30
  "quant_method": "bitsandbytes"
31
  },
32
- "rms_norm_eps": 1e-06,
33
  "rope_scaling": null,
34
- "rope_theta": 1000000.0,
35
- "sliding_window": null,
36
- "tie_word_embeddings": true,
37
  "torch_dtype": "float16",
38
  "transformers_version": "4.44.2",
39
  "unsloth_version": "2024.9.post4",
40
  "use_cache": true,
41
- "use_mrope": false,
42
- "use_sliding_window": false,
43
- "vocab_size": 151936
44
  }
 
1
  {
2
+ "_name_or_path": "unsloth/tinyllama-bnb-4bit",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
  "hidden_act": "silu",
11
  "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 5632,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 22,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
  "quantization_config": {
23
  "bnb_4bit_compute_dtype": "float16",
24
  "bnb_4bit_quant_type": "nf4",
 
31
  "load_in_8bit": false,
32
  "quant_method": "bitsandbytes"
33
  },
34
+ "rms_norm_eps": 1e-05,
35
  "rope_scaling": null,
36
+ "rope_theta": 10000.0,
37
+ "tie_word_embeddings": false,
 
38
  "torch_dtype": "float16",
39
  "transformers_version": "4.44.2",
40
  "unsloth_version": "2024.9.post4",
41
  "use_cache": true,
42
+ "vocab_size": 32000
 
 
43
  }
generation_config.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "bos_token_id": 151643,
3
- "eos_token_id": 151643,
4
- "max_length": 32768,
5
- "max_new_tokens": 2048,
6
- "pad_token_id": 151665,
7
  "transformers_version": "4.44.2"
8
  }
 
1
  {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
 
6
  "transformers_version": "4.44.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6849d8056dca58438a3c2cb39d0b475634485b8e4f02586a8f079df068ff6a44
3
- size 2676955807
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6b88efc28e5f82be67140f852de51a47b8e823828b6a27eee535499e75e795
3
+ size 762453353