Hugging Face's logo

deepnet
/
C4ReadyModel3

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
Community
deepnet commited on
Commit
c81e2a2
·
verified ·
1 Parent(s): 9c1db06

Upload LlamaForCausalLM

Browse files
Files changed (9) hide show
  1. config.json +3 -10
  2. generation_config.json +1 -2
  3. model-00001-of-00006.safetensors +2 -2
  4. model-00002-of-00006.safetensors +1 -1
  5. model-00003-of-00006.safetensors +1 -1
  6. model-00004-of-00006.safetensors +1 -1
  7. model-00005-of-00006.safetensors +1 -1
  8. model-00006-of-00006.safetensors +2 -2
  9. model.safetensors.index.json +1 -1
config.json CHANGED
@@ -1,36 +1,29 @@
1
  {
2
- "_name_or_path": "BestLlamaSN9/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 100257,
9
- "device": "cuda:0",
10
- "dtype": "bfloat16",
11
  "eos_token_id": 100257,
12
  "hidden_act": "silu",
13
  "hidden_size": 4096,
14
  "initializer_range": 0.02,
15
  "intermediate_size": 14208,
16
- "leave_empty": true,
17
  "max_position_embeddings": 4096,
18
  "mlp_bias": false,
19
  "model_type": "llama",
20
  "num_attention_heads": 32,
21
  "num_hidden_layers": 60,
22
  "num_key_value_heads": 8,
23
- "pop_states_at_layer": null,
24
  "pretraining_tp": 1,
25
- "return_states_at_layer": null,
26
  "rms_norm_eps": 1e-05,
27
  "rope_scaling": null,
28
  "rope_theta": 500000.0,
29
- "start_at_layer": null,
30
- "stash_states_at_layer": null,
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.44.1",
34
- "use_cache": false,
35
- "vocab_size": 96000
36
  }
 
1
  {
2
+ "_name_or_path": "BestLlamaSN9-2/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 100257,
 
 
9
  "eos_token_id": 100257,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14208,
 
14
  "max_position_embeddings": 4096,
15
  "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
18
  "num_hidden_layers": 60,
19
  "num_key_value_heads": 8,
 
20
  "pretraining_tp": 1,
 
21
  "rms_norm_eps": 1e-05,
22
  "rope_scaling": null,
23
  "rope_theta": 500000.0,
 
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.1",
27
+ "use_cache": true,
28
+ "vocab_size": 100288
29
  }
generation_config.json CHANGED
@@ -2,6 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 100257,
4
  "eos_token_id": 100257,
5
- "transformers_version": "4.44.1",
6
- "use_cache": false
7
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 100257,
4
  "eos_token_id": 100257,
5
+ "transformers_version": "4.44.1"
 
6
  }
model-00001-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:976e8976d4a40d4b1c7c6362abe4544584b925b848dd14c6453e75fa9e25b756
3
- size 4884424560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c2f3c27f30abbdc932ec4fc93cbdb051fe1e475e17c3935883f3b7d5eff3f1
3
+ size 4919551856
model-00002-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e677e5755b346cc33015e2a1a00ad6904fc719878c9d9cbce9e7a5266cfbc06
3
  size 4996673256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f93fcb1117feecb6637fe3a095b45b9447509251cc95f860d9ee48d2c167f6
3
  size 4996673256
model-00003-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d056d7e22ccdb347ec5936afdb2885df4f2521c44b2cc250a0058969eaee198c
3
  size 4964151144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89867ef5e3d8c535b6e27ccf4c7c181585853195ca5e668d938e15c43aebe1b
3
  size 4964151144
model-00004-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b82ea72cc17e63a8d2082821c5201fb33cade7b6a526314bac96244b08de0b5b
3
  size 4996673264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8dcd96de37366114ecb25a8bf300acb9d38d309d3363ea0cf2c9f677a33875
3
  size 4996673264
model-00005-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f19d091ad7c15ca1fb7b249ecddce39aa3e0ab03d5cd05260da325d10fcd4eb
3
  size 4964151144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:579541b16dcd8a06c0e0d2f6b573870ca446a2a0a22b2d8cadd19e1a0b89570a
3
  size 4964151144
model-00006-of-00006.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:776b8957b3e19c547cc55a78a6b051a5ecfec9523937b8f601d17ee15651d397
3
- size 2751558416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce473c17678b1387b875802046f6bb06d5e3e745a8c8f69d0a0f006c062b4435
3
+ size 2786685712
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 27557568512
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00006-of-00006.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 27627823104
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00006-of-00006.safetensors",