jsaizant commited on
Commit
6416025
·
verified ·
1 Parent(s): 70b8f95

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +57 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/gpfs/projects/bsc88/text/models/salamandra_quantized_speculative/V1.1/salamandra-2b-instruct-gptq",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 5440,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "num_key_value_heads": 16,
21
+ "pretraining_tp": 1,
22
+ "quantization_config": {
23
+ "backend": null,
24
+ "batch_size": 1,
25
+ "bits": 4,
26
+ "block_name_to_quantize": null,
27
+ "cache_block_outputs": true,
28
+ "checkpoint_format": "gptq",
29
+ "damp_percent": 0.1,
30
+ "dataset": null,
31
+ "desc_act": false,
32
+ "exllama_config": {
33
+ "version": 1
34
+ },
35
+ "group_size": 64,
36
+ "max_input_length": null,
37
+ "meta": null,
38
+ "model_seqlen": null,
39
+ "module_name_preceding_first_block": null,
40
+ "modules_in_block_to_quantize": null,
41
+ "pad_token_id": null,
42
+ "quant_method": "gptq",
43
+ "sym": true,
44
+ "tokenizer": null,
45
+ "true_sequential": true,
46
+ "use_cuda_fp16": false,
47
+ "use_exllama": true
48
+ },
49
+ "rms_norm_eps": 1e-05,
50
+ "rope_scaling": null,
51
+ "rope_theta": 10000.0,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "float16",
54
+ "transformers_version": "4.49.0",
55
+ "use_cache": true,
56
+ "vocab_size": 256000
57
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.49.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8c2e21d5c72bbd141a08b5e4813d6febcb4ff71e29762b1f7b2651d01f4d56
3
+ size 2748604656