sharpenb commited on
Commit
828b54a
1 Parent(s): 25e9263

Upload folder using huggingface_hub (#1)

Browse files

- 21638378d0fd4f48a9e506cbd6770c28470ab90a88e3a7d82c94d7242252f1e5 (564506088833d3126b7220cf74e3c7aca162379f)
- 06972b0d4b37d4be4fe567adb99b37a54ea255a219cf9767cbb1ccb08d0ec784 (682cc642faf26e0c2fa1adc58d507722f68b8f57)

config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mattshumer/Hermes-2-Pro-11B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 50,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "bnb_4bit_compute_dtype": "float32",
20
+ "bnb_4bit_quant_type": "fp4",
21
+ "bnb_4bit_use_double_quant": true,
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": [
25
+ "lm_head"
26
+ ],
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": true,
29
+ "load_in_8bit": false,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_theta": 10000.0,
34
+ "sliding_window": 4096,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.37.2",
38
+ "use_cache": false,
39
+ "vocab_size": 32032
40
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "transformers_version": "4.37.2",
6
+ "use_cache": false
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5311bffa1e8caf22d00301270978b20c1bb2da973e8eb7998802020ee5a0f938
3
+ size 5000054986
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d54278dd4097eb73fe5693103f77c8bed574f20cf9b6f77cf494a7e01bba7e
3
+ size 1151939496
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff