Chrisfrancisque commited on
Commit
a331bc2
·
verified ·
1 Parent(s): a420c6e

Upload FFT model trained on coding datasets

Browse files
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: llama2
5
+ tags:
6
+ - code
7
+ - llama2
8
+ - full-fine-tuning
9
+ - mask-fine-tuning
10
+ - coding
11
+ datasets:
12
+ - tulu3_persona_python
13
+ - evol_code
14
+ - code_alpaca
15
+ base_model: meta-llama/Llama-2-7b-hf
16
+ ---
17
+
18
+ # llama2-7b-coding-fft
19
+
20
+ This model is a **Full Fine-Tuned (FFT)** version of LLaMA2-7B on coding datasets, trained as part of replicating the [Mask Fine-Tuning (MFT) paper](https://arxiv.org/abs/2503.22764v1).
21
+
22
+ ## Model Details
23
+
24
+ - **Base Model:** meta-llama/Llama-2-7b-hf
25
+ - **Training Type:** Full Fine-Tuning (FFT)
26
+ - **Domain:** Coding
27
+ - **Hardware:** TPU v4-8
28
+ - **Training Framework:** PyTorch + torch_xla
29
+
30
+ ## Training Data
31
+
32
+ The model was trained on 30,000 samples from three coding datasets (matching the paper):
33
+ - **Tulu 3 Persona Python:** 10,000 samples
34
+ - **Evol CodeAlpaca:** 10,000 samples
35
+ - **Code-Alpaca:** 10,000 samples
36
+
37
+ ## Training Configuration
38
+
39
+ - **Epochs:** 2
40
+ - **Sequence Length:** 4096
41
+ - **Learning Rate:** 2e-5
42
+ - **Batch Size:** 8 (effective)
43
+ - **Optimizer:** AdamW
44
+ - **LR Scheduler:** Linear with warmup
45
+ - **Mixed Precision:** bfloat16
46
+
47
+ ## Training Results
48
+
49
+ - **Final Loss:** 0.15353151041666666
50
+ - **Final Perplexity:** 1.1673020833333334
51
+ - **Training Time:** ~7 hours on TPU v4-8
52
+ - **Total Steps:** 7500
53
+
54
+ ### Loss Progression
55
+ - Epoch 0: 0.42591484375
56
+ - Epoch 1: 0.15353151041666666
57
+
58
+ ## Intended Use
59
+
60
+ This model serves as the **FFT baseline** for the Mask Fine-Tuning paper replication. It will be evaluated on:
61
+ - **HumanEval** (code generation benchmark)
62
+ - Target: Match paper's FFT baseline of 29.3%
63
+
64
+ ## Evaluation
65
+
66
+ Evaluation on HumanEval is pending. Results will be updated here once available.
67
+
68
+ ## Citation
69
+
70
+ If you use this model, please cite the original MFT paper:
71
+
72
+ ```bibtex
73
+ @article{mft2025,
74
+ title={Mask Fine-Tuning},
75
+ author={[Authors from paper]},
76
+ journal={arXiv preprint arXiv:2503.22764v1},
77
+ year={2025}
78
+ }
79
+ ```
80
+
81
+ ## Reproducibility
82
+
83
+ Training configuration and code available at: [GitHub Repository](https://github.com/chrisfrancisque/mft-tpu)
84
+
85
+ ## License
86
+
87
+ This model inherits the LLaMA 2 Community License from the base model.
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.35.0",
26
+ "use_cache": false,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.35.0"
10
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9d73260373633db6089491a758c1644a79386bed570483db8f87e6519b5d4e
3
+ size 4969455504
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32d62b65b1783d62146538a764b53b25068461700042d6a120ee8bf942dd4cf
3
+ size 1506886544
model.safetensors.index.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6476267520
4
+ },
5
+ "weight_map": {
6
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.28._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.29._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.30._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_input_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_down_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_gate_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_mlp_FSDP_SHARD_SEPARATOR_up_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_post_attention_layernorm_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_k_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_o_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_q_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9._fsdp_shard_FSDP_SHARD_SEPARATOR__fsdp_wrapped_module_FSDP_SHARD_SEPARATOR__fpw_module_FSDP_SHARD_SEPARATOR_self_attn_FSDP_SHARD_SEPARATOR_v_proj_FSDP_SHARD_SEPARATOR_weight": "model-00001-of-00002.safetensors"
294
+ }
295
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
35
+ "padding_side": "right",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }