akhooli commited on
Commit
93ac433
1 Parent(s): 1d455b6

Upload LlamaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "FreedomIntelligence/AceGPT-v2-32B-Chat",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151643,
9
+ "eos_token_id": 151643,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 27392,
14
+ "max_position_embeddings": 32768,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 40,
18
+ "num_hidden_layers": 64,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "quantization_config": {
23
+ "_load_in_4bit": true,
24
+ "_load_in_8bit": false,
25
+ "bnb_4bit_compute_dtype": "float32",
26
+ "bnb_4bit_quant_storage": "uint8",
27
+ "bnb_4bit_quant_type": "fp4",
28
+ "bnb_4bit_use_double_quant": false,
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": 1000000.0,
40
+ "tie_word_embeddings": false,
41
+ "torch_dtype": "float16",
42
+ "transformers_version": "4.44.0",
43
+ "use_cache": true,
44
+ "vocab_size": 152064
45
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.0"
7
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0f6da01a9dce55fab8c8456299d8af7a056830a2179144aaa767f27baf06a1
3
+ size 4936719310
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5d8c837da1b90651d70778e4aaf97687ccf70dc163eb5cf5f8306efe5c1025
3
+ size 4976805766
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be74b1098281d0a77cb79c18c8bd340d040203ab91797aa293e06aca454391f
3
+ size 4997486873
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2cb04cf357419d6ee70f30e934c0b5b10ff6870f2a831a48c3fec558e8aedad
3
+ size 4060946707
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561fa82b4a9862d93658dfedd8fe685ee8575e501bba91ce7d626f5be257b0b9
3
+ size 1557135488
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff