RahulPi commited on
Commit
6b2e62d
·
verified ·
1 Parent(s): 39ca41f

(Trained with Unsloth)

Browse files
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 100257,
8
+ "torch_dtype": "float16",
9
+ "eos_token_id": 100265,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 17920,
15
+ "max_position_embeddings": 16384,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 40,
19
+ "num_hidden_layers": 40,
20
+ "num_key_value_heads": 10,
21
+ "original_max_position_embeddings": 16384,
22
+ "pad_token_id": 100351,
23
+ "pretraining_tp": 1,
24
+ "quantization_config": {
25
+ "bnb_4bit_compute_dtype": "float16",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": true,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": [
31
+ "model.layers.1.mlp.gate_proj",
32
+ "model.layers.1.mlp.up_proj",
33
+ "model.layers.1.mlp.down_proj",
34
+ "model.layers.2.mlp.gate_proj",
35
+ "model.layers.2.mlp.up_proj",
36
+ "model.layers.2.mlp.down_proj",
37
+ "model.layers.3.mlp.gate_proj",
38
+ "model.layers.3.mlp.up_proj",
39
+ "model.layers.3.mlp.down_proj",
40
+ "model.layers.37.self_attn.o_proj",
41
+ "model.layers.39.self_attn.o_proj",
42
+ "lm_head"
43
+ ],
44
+ "llm_int8_threshold": 6.0,
45
+ "load_in_4bit": true,
46
+ "load_in_8bit": false,
47
+ "quant_method": "bitsandbytes"
48
+ },
49
+ "rms_norm_eps": 1e-05,
50
+ "rope_scaling": null,
51
+ "rope_theta": 250000,
52
+ "tie_word_embeddings": false,
53
+ "transformers_version": "4.57.1",
54
+ "unsloth_fixed": true,
55
+ "unsloth_version": "2025.10.12",
56
+ "use_cache": true,
57
+ "vocab_size": 100352
58
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": [
5
+ 100265
6
+ ],
7
+ "max_length": 16384,
8
+ "pad_token_id": 100351,
9
+ "transformers_version": "4.57.1"
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb5c173615533790feef23927756da40155be102b753b2a6c04930485d5189e
3
+ size 4971805372
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb7319ee8c67d86e45a128bdfb1d8a4d974fbfa3f74e7f45a3a3059aa49d50b
3
+ size 4392572543
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57010d961bd3e9561280b0d17a44cee4e190362cbf21cd51c5c331c92c778cb7
3
+ size 1027604608
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff