Upload 8 files

README.md

@@ -0,0 +1,38 @@
+---
+license: mit
+---
+
+This is a reproduction of the <a href="https://arxiv.org/abs/2402.17764"> BitNet b1.58</a> paper. The models are trained with <a href="https://github.com/togethercomputer/RedPajama-Data">RedPajama dataset</a> for 100B tokens. The hypers, as well as two-stage LR and weight decay, are implemented as suggested in their following <a href="https://github.com/microsoft/unilm/blob/master/bitnet/The-Era-of-1-bit-LLMs__Training_Tips_Code_FAQ.pdf">paper</a>. All models are open-source in the <a href="https://huggingface.co/1bitLLM">repo</a>. We will train larger models and/or more tokens when resource is available.
+
+## Results
+PPL and zero-shot accuracy:
+| Models | PPL| ARCe| ARCc| HS | BQ | OQ | PQ | WGe | Avg
+|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|
+| FP16 700M (reported) | 12.33 | 54.7 | 23.0 | 37.0 | 60.0 | 20.2 | 68.9 | 54.8 | 45.5 |
+| BitNet b1.58 700M (reported) | 12.87 | 51.8 | 21.4 | 35.1 | 58.2 | 20.0 | 68.1 | 55.2 | 44.3 |
+| BitNet b1.58 700M (reproduced) | 12.78 | 51.4 | 21.8 | 35.0 | 59.6 | 20.6 | 67.5 | 55.4 | 44.5 |
+| FP16 1.3B (reported)    | 11.25  | 56.9 | 23.5 | 38.5 | 59.1 | 21.6 | 70.0 | 53.9 | 46.2
+| BitNet b1.58 1.3B (reported)    | 11.29  | 54.9 | 24.2 | 37.7 | 56.7 | 19.6 | 68.8 | 55.8 | 45.4 |
+| BitNet b1.58 1.3B (reproduced)    | 11.19 | 55.8 | 23.7 | 37.6 | 59.0 | 20.2 | 69.2 | 56.0 | 45.9
+| FP16 3B (reported)    | 10.04   | 62.1 | 25.6 | 43.3 | 61.8 | 24.6 | 72.1 | 58.2 | 49.7
+| BitNet b1.58 3B (reported)    | 9.91   | 61.4 | 28.3 | 42.9 | 61.5 | 26.6 | 71.5 | 59.3 | 50.2
+| BitNet b1.58 3B (reproduced)    | 9.88 | 60.9 | 28.0 | 42.3 | 58.3 | 26.0 | 71.4 | 60.3 | 49.6 |
+
+The differences between the reported numbers and the reproduced results are possibly variances from the training data processing, seeds, or other random factors.
+
+## Evaluation
+The evaluation pipelines are from the paper authors. Here is the commands to run the evaluation:
+```
+pip install lm-eval==0.3.0
+```
+```
+python eval_ppl.py --hf_path 1bitLLM/bitnet_b1_58-3B --seqlen 2048
+```
+```
+python eval_task.py --hf_path 1bitLLM/bitnet_b1_58-3B \
+    --batch_size 1 \
+    --tasks \
+    --output_path result.json \
+    --num_fewshot 0 \
+    --ctx_size 2048
+```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "1bitLLM/bitnet_b1_58-3B",
+  "_name_or_path": "1bitLLM/bitnet_b1_58-xl",
   "architectures": [
     "BitnetForCausalLM"
   ],
@@ -8,14 +8,14 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
-  "hidden_size": 3200,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
   "input_bits": 8,
-  "intermediate_size": 8640,
+  "intermediate_size": 5460,
   "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
-  "num_hidden_layers": 26,
+  "num_hidden_layers": 24,
   "num_key_value_heads": 32,
   "pad_token_id": 32000,
   "pretraining_tp": 1,

model.safetensors.index.json

@@ -1,321 +1,297 @@
 {
   "metadata": {
-    "total_size": 13297556560
+    "total_size": 5094337408
   },
   "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.mlp.ffn_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.19.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.mlp.ffn_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.self_attn.inner_attn_ln.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.mlp.ffn_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.self_attn.inner_attn_ln.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.ffn_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.inner_attn_ln.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.ffn_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.inner_attn_ln.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.ffn_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.inner_attn_ln.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.ffn_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.inner_attn_ln.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.ffn_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.inner_attn_ln.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.ffn_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.inner_attn_ln.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "model.norm.weight": "model-00003-of-00003.safetensors"
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.ffn_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.ffn_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.inner_attn_ln.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }