Hugging Face's logo

jonybepary
/
awazz_ai

Text Generation
Transformers
PyTorch
GGUF
llama
text-generation-inference
Inference Endpoints
Model card Files Community
jonybepary commited on
Commit
f494001
•
1 Parent(s): a264c32

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +19 -27
  2. generation_config.json +5 -4
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,34 +1,26 @@
1
  {
2
- "_name_or_path": "/content/sft_santacoder1b/final_merged_checkpoint/",
3
- "activation_function": "gelu_pytorch_tanh",
4
  "architectures": [
5
- "GPTBigCodeForCausalLM"
6
  ],
7
- "attention_softmax_in_fp32": true,
8
- "attn_pdrop": 0.1,
9
- "bos_token_id": 49152,
10
- "embd_pdrop": 0.1,
11
- "eos_token_id": 49152,
12
  "initializer_range": 0.02,
13
- "layer_norm_epsilon": 1e-05,
14
- "model_type": "gpt_bigcode",
15
- "multi_query": true,
16
- "n_embd": 2048,
17
- "n_head": 16,
18
- "n_inner": 8192,
19
- "n_layer": 24,
20
- "n_positions": 2048,
21
- "resid_pdrop": 0.1,
22
- "runner_max_sequence_length": null,
23
- "scale_attention_softmax_in_fp32": true,
24
- "scale_attn_weights": true,
25
- "summary_activation": null,
26
- "summary_first_dropout": 0.1,
27
- "summary_proj_to_labels": true,
28
- "summary_type": "cls_index",
29
- "summary_use_proj": true,
30
  "torch_dtype": "float16",
31
- "transformers_version": "4.32.1",
32
  "use_cache": true,
33
- "vocab_size": 49280
34
  }
 
1
  {
2
+ "_name_or_path": "/content/sft_llama2_7b_chat_uncensored/final_merged_checkpoint/",
 
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
 
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 5632,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 22,
16
+ "num_key_value_heads": 4,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
 
 
 
 
 
 
22
  "torch_dtype": "float16",
23
+ "transformers_version": "4.33.1",
24
  "use_cache": true,
25
+ "vocab_size": 32000
26
  }
generation_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 49152,
4
- "eos_token_id": 49152,
5
- "transformers_version": "4.32.1"
 
6
  }
 
1
  {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.33.1"
7
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fb01dee3328495ad1ecac6b399db486baa5770495ad5417da3869cd07ce8690
3
- size 2249864157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84cac137f84bcafcdc24df180dff1ce8e46ef741247b484f9d1180517e361942
3
+ size 2200161457