nroggendorff commited on
Commit
22e2669
1 Parent(s): fbab81d

2.1059732666015627

Browse files
Files changed (4) hide show
  1. README.md +3 -1
  2. config.json +45 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,6 +1,8 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: transformers
3
+ tags:
4
+ - trl
5
+ - sft
6
  ---
7
 
8
  # Model Card for Model ID
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "nroggendorff/smallerama",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 64,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 256,
14
+ "max_position_embeddings": 128,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 1,
18
+ "num_hidden_layers": 2,
19
+ "num_key_value_heads": 1,
20
+ "pad_token_id": 1,
21
+ "pretraining_tp": 1,
22
+ "quantization_config": {
23
+ "_load_in_4bit": true,
24
+ "_load_in_8bit": false,
25
+ "bnb_4bit_compute_dtype": "bfloat16",
26
+ "bnb_4bit_quant_storage": "uint8",
27
+ "bnb_4bit_quant_type": "nf4",
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,
35
+ "quant_method": "bitsandbytes"
36
+ },
37
+ "rms_norm_eps": 1e-06,
38
+ "rope_scaling": null,
39
+ "rope_theta": 10000.0,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.43.3",
43
+ "use_cache": true,
44
+ "vocab_size": 32000
45
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.43.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe93fbb5bd78465221187f43b66bd3e93e3c25d02d9da11acf216f0c9359dc13
3
+ size 16481029