Hugging Face's logo

sara219
/
OrpoLlama-3-8B

Text Generation
Transformers
Safetensors
phi3
trl
orpo
conversational
custom_code
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
sara219 commited on
Commit
f0ed2e5
•
1 Parent(s): 66909ae

Upload Phi3ForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +3 -1
  2. config.json +36 -16
  3. generation_config.json +4 -7
  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
+ - orpo
6
  ---
7
 
8
  # Model Card for Model ID
config.json CHANGED
@@ -1,30 +1,50 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
  "attention_dropout": 0.0,
8
- "bos_token_id": 128256,
9
- "eos_token_id": 128257,
 
 
 
 
 
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
- "pad_token_id": 128257,
21
- "pretraining_tp": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "rms_norm_eps": 1e-05,
23
  "rope_scaling": null,
24
- "rope_theta": 500000.0,
 
25
  "tie_word_embeddings": false,
26
- "torch_dtype": "float16",
27
  "transformers_version": "4.41.2",
28
  "use_cache": true,
29
- "vocab_size": 128258
30
  }
 
1
  {
2
+ "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
3
  "architectures": [
4
+ "Phi3ForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 32011,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32012,
14
  "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
  "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 4096,
19
+ "model_type": "phi3",
 
20
  "num_attention_heads": 32,
21
  "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "original_max_position_embeddings": 4096,
24
+ "pad_token_id": 32012,
25
+ "quantization_config": {
26
+ "_load_in_4bit": true,
27
+ "_load_in_8bit": false,
28
+ "bnb_4bit_compute_dtype": "float16",
29
+ "bnb_4bit_quant_storage": "uint8",
30
+ "bnb_4bit_quant_type": "nf4",
31
+ "bnb_4bit_use_double_quant": true,
32
+ "llm_int8_enable_fp32_cpu_offload": false,
33
+ "llm_int8_has_fp16_weight": false,
34
+ "llm_int8_skip_modules": null,
35
+ "llm_int8_threshold": 6.0,
36
+ "load_in_4bit": true,
37
+ "load_in_8bit": false,
38
+ "quant_method": "bitsandbytes"
39
+ },
40
+ "resid_pdrop": 0.0,
41
  "rms_norm_eps": 1e-05,
42
  "rope_scaling": null,
43
+ "rope_theta": 10000.0,
44
+ "sliding_window": 2047,
45
  "tie_word_embeddings": false,
46
+ "torch_dtype": "float32",
47
  "transformers_version": "4.41.2",
48
  "use_cache": true,
49
+ "vocab_size": 32013
50
  }
generation_config.json CHANGED
@@ -1,10 +1,7 @@
1
  {
2
- "bos_token_id": 128256,
3
- "do_sample": true,
4
- "eos_token_id": 128257,
5
- "max_length": 4096,
6
- "pad_token_id": 128257,
7
- "temperature": 0.6,
8
- "top_p": 0.9,
9
  "transformers_version": "4.41.2"
10
  }
 
1
  {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 32011,
4
+ "eos_token_id": 32012,
5
+ "pad_token_id": 32012,
 
 
 
6
  "transformers_version": "4.41.2"
7
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5f240baec74d082ddd7abc3325cf44e509e632319ab5bdb49272c054b1d3ba
3
+ size 2692932856