Hugging Face's logo

Shaleen123
/
test

PEFT
Safetensors
gpt2
4-bit precision
bitsandbytes
Model card Files Community
Shaleen123 commited on
Commit
c5a00cb
·
verified ·
1 Parent(s): c816f42

Upload model

Browse files
Files changed (3) hide show
  1. config.json +38 -25
  2. generation_config.json +4 -9
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,26 +1,28 @@
1
  {
2
- "_name_or_path": "01-ai/Yi-6B-Chat",
 
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": 4096,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 11008,
14
- "max_position_embeddings": 4096,
15
- "model_type": "llama",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 4,
19
- "pretraining_tp": 1,
 
20
  "quantization_config": {
21
- "bnb_4bit_compute_dtype": "float32",
22
- "bnb_4bit_quant_type": "fp4",
23
- "bnb_4bit_use_double_quant": false,
 
 
24
  "llm_int8_enable_fp32_cpu_offload": false,
25
  "llm_int8_has_fp16_weight": false,
26
  "llm_int8_skip_modules": null,
@@ -29,12 +31,23 @@
29
  "load_in_8bit": false,
30
  "quant_method": "bitsandbytes"
31
  },
32
- "rms_norm_eps": 1e-05,
33
- "rope_scaling": null,
34
- "rope_theta": 5000000.0,
35
- "tie_word_embeddings": false,
36
- "torch_dtype": "float16",
37
- "transformers_version": "4.38.0.dev0",
 
 
 
 
 
 
 
 
 
 
 
38
  "use_cache": false,
39
- "vocab_size": 64000
40
  }
 
1
  {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
 
 
11
  "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
  "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "bfloat16",
24
+ "bnb_4bit_quant_type": "nf4",
25
+ "bnb_4bit_use_double_quant": true,
26
  "llm_int8_enable_fp32_cpu_offload": false,
27
  "llm_int8_has_fp16_weight": false,
28
  "llm_int8_skip_modules": null,
 
31
  "load_in_8bit": false,
32
  "quant_method": "bitsandbytes"
33
  },
34
+ "reorder_and_upcast_attn": false,
35
+ "resid_pdrop": 0.1,
36
+ "scale_attn_by_inverse_layer_idx": false,
37
+ "scale_attn_weights": true,
38
+ "summary_activation": null,
39
+ "summary_first_dropout": 0.1,
40
+ "summary_proj_to_labels": true,
41
+ "summary_type": "cls_index",
42
+ "summary_use_proj": true,
43
+ "task_specific_params": {
44
+ "text-generation": {
45
+ "do_sample": true,
46
+ "max_length": 50
47
+ }
48
+ },
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.38.0",
51
  "use_cache": false,
52
+ "vocab_size": 50257
53
  }
generation_config.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
- "bos_token_id": 6,
3
- "do_sample": true,
4
- "eos_token_id": 64001,
5
- "max_length": 4096,
6
- "max_new_tokens": 200,
7
- "pad_token_id": 64001,
8
- "temperature": 0.7,
9
- "top_p": 0.7,
10
- "transformers_version": "4.38.0.dev0"
11
  }
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.38.0"
 
 
 
 
 
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fda1fa666c14657e36280c9f7e2471b6cf3a674b57f1d667f391053f152c9eb6
3
- size 4163527680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a1981a230bd8a1e56fe3b4d37fcf2992cf43f4231242473d72ddd6f6fce5178
3
+ size 201919718