DatPySci commited on
Commit
919b6bb
·
verified ·
1 Parent(s): d7103ea

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +48 -0
  2. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/config.json +36 -0
  3. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/model.safetensors.index.json +263 -0
  4. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/tokenizer.json +3 -0
  5. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/data.pt +3 -0
  6. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/tokenizer.json +3 -0
  7. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/data.pt +3 -0
  8. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/config.json +36 -0
  9. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/model.safetensors.index.json +263 -0
  10. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/tokenizer.json +3 -0
  11. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/data.pt +3 -0
  12. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/tokenizer.json +3 -0
  13. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/data.pt +3 -0
  14. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/tokenizer.json +3 -0
  15. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/data.pt +3 -0
  16. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/tokenizer.json +3 -0
  17. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/data.pt +3 -0
  18. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/tokenizer.json +3 -0
  19. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/data.pt +3 -0
  20. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/tokenizer.json +3 -0
  21. Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/data.pt +3 -0
  22. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/chat_template.jinja +93 -0
  23. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/generation_config.json +12 -0
  24. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/tokenizer.json +3 -0
  25. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/data.pt +3 -0
  26. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/generation_config.json +12 -0
  27. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/tokenizer.json +3 -0
  28. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/data.pt +3 -0
  29. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/model.safetensors.index.json +263 -0
  30. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/tokenizer.json +3 -0
  31. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/data.pt +3 -0
  32. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/tokenizer.json +3 -0
  33. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/data.pt +3 -0
  34. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/actor_hf/tokenizer.json +3 -0
  35. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/data.pt +3 -0
  36. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/tokenizer.json +3 -0
  37. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/data.pt +3 -0
  38. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/special_tokens_map.json +23 -0
  39. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/tokenizer.json +3 -0
  40. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/data.pt +3 -0
  41. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/chat_template.jinja +93 -0
  42. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/tokenizer.json +3 -0
  43. Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/data.pt +3 -0
  44. Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/tokenizer.json +3 -0
  45. Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/data.pt +3 -0
  46. Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/actor_hf/tokenizer.json +3 -0
  47. Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/data.pt +3 -0
  48. Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/actor_hf/tokenizer.json +3 -0
  49. Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/data.pt +3 -0
  50. Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/tokenizer.json +3 -0
.gitattributes CHANGED
@@ -66,3 +66,51 @@ Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step320/huggingface/tokenizer.json
66
  Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step384/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
  Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step448/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
  Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step512/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step384/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
  Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step448/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
  Qwen2.5-3B-Instruct-polaris-AdamW-GRPO/bsz256/step512/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
83
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
87
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
88
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
89
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
90
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
94
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
95
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
97
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
99
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
100
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
101
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
102
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz64/global_step_512/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
103
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_448/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
104
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
105
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
106
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_256/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
107
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
108
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
109
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_128/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
110
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz512/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
111
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
112
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
113
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
114
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz32/global_step_384/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
115
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
116
+ Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_64/actor_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 24,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128009,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 32.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": true,
33
+ "transformers_version": "4.57.6",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/model.safetensors.index.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3606752256,
4
+ "total_size": 7213504512
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.norm.weight": "model-00001-of-00002.safetensors"
262
+ }
263
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_128/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b60420b38e3302a21bd366d20b658b5900dd58ff26af25c9e491a25f9f742e
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_192/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1426eb185c2e59b5dd172e4ce347b8ca61db3f326de58caf219f11808d4b7d8d
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 24,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128009,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 32.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": true,
33
+ "transformers_version": "4.57.6",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/model.safetensors.index.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3606752256,
4
+ "total_size": 7213504512
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00002-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.norm.weight": "model-00001-of-00002.safetensors"
262
+ }
263
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_256/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04905734c7cd81459148de025dcefbbd71faedbb192f80bb1428a68359f3bd0c
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_320/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9987b911ad60991c5ce55862d0a5c42c3c5fd484d09a61b8dbbdb2809965380a
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_384/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52f2d40020496584f3fd9e63f6f7ce92dffb6d87aa6a9de73c53b060450e1d6
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_448/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90efb4c91cf8b5d5cc7fd7f865b1435c6194485959c0d92591cf99d804b4243a
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_512/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab2fecc49baeb8ed6ffcf084d50cf335608919dc1dfdde27320b3bd33ab3677
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz128/global_step_64/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c471db77d3351cc66bc966e78cb113ec6095e82ecbbb87a4a9dc52d2955247
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.57.6"
12
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_128/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eace4e39b4b3f488dbf3221fa39e8bd3fd51b0eb3e14f6c5a6c8c63340ca66e
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.57.6"
12
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_192/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44ecb421ff4960f5d637c136454a7665370c1662a9a9e09fbeaca092a0be9aa
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/model.safetensors.index.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 3606752256,
4
+ "total_size": 7213504512
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.norm.weight": "model-00001-of-00002.safetensors"
262
+ }
263
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_256/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7372699cc74ebaff4ff9def047435117037f9d5b3174f1b6de4116292d03f622
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_320/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c3d407d7f44a8ca6f1ce8410be25e7f4d3ba82c589e4455fa369ab6329637b
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_384/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e52eb58b2e8ee6cedd1576fca196db8794658f365888b5270df24df9899b6352
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_448/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f5498bfa6ab46eca706f5172d3e16fdd0386d01aeb674a3b943602ec4d4e136
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_512/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12db7cbcbc52442c9a0e4b58089ab2177c086feeb2bdfb34fec66e8f7430d96c
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/chat_template.jinja ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- if strftime_now is defined %}
10
+ {%- set date_string = strftime_now("%d %b %Y") %}
11
+ {%- else %}
12
+ {%- set date_string = "26 Jul 2024" %}
13
+ {%- endif %}
14
+ {%- endif %}
15
+ {%- if not tools is defined %}
16
+ {%- set tools = none %}
17
+ {%- endif %}
18
+
19
+ {#- This block extracts the system message, so we can slot it into the right place. #}
20
+ {%- if messages[0]['role'] == 'system' %}
21
+ {%- set system_message = messages[0]['content']|trim %}
22
+ {%- set messages = messages[1:] %}
23
+ {%- else %}
24
+ {%- set system_message = "" %}
25
+ {%- endif %}
26
+
27
+ {#- System message #}
28
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
29
+ {%- if tools is not none %}
30
+ {{- "Environment: ipython\n" }}
31
+ {%- endif %}
32
+ {{- "Cutting Knowledge Date: December 2023\n" }}
33
+ {{- "Today Date: " + date_string + "\n\n" }}
34
+ {%- if tools is not none and not tools_in_user_message %}
35
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
36
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
37
+ {{- "Do not use variables.\n\n" }}
38
+ {%- for t in tools %}
39
+ {{- t | tojson(indent=4) }}
40
+ {{- "\n\n" }}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {{- system_message }}
44
+ {{- "<|eot_id|>" }}
45
+
46
+ {#- Custom tools are passed in a user message with some extra guidance #}
47
+ {%- if tools_in_user_message and not tools is none %}
48
+ {#- Extract the first user message so we can plug it in here #}
49
+ {%- if messages | length != 0 %}
50
+ {%- set first_user_message = messages[0]['content']|trim %}
51
+ {%- set messages = messages[1:] %}
52
+ {%- else %}
53
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
54
+ {%- endif %}
55
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
56
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
57
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
58
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
59
+ {{- "Do not use variables.\n\n" }}
60
+ {%- for t in tools %}
61
+ {{- t | tojson(indent=4) }}
62
+ {{- "\n\n" }}
63
+ {%- endfor %}
64
+ {{- first_user_message + "<|eot_id|>"}}
65
+ {%- endif %}
66
+
67
+ {%- for message in messages %}
68
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
69
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
70
+ {%- elif 'tool_calls' in message %}
71
+ {%- if not message.tool_calls|length == 1 %}
72
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
73
+ {%- endif %}
74
+ {%- set tool_call = message.tool_calls[0].function %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- '{"name": "' + tool_call.name + '", ' }}
77
+ {{- '"parameters": ' }}
78
+ {{- tool_call.arguments | tojson }}
79
+ {{- "}" }}
80
+ {{- "<|eot_id|>" }}
81
+ {%- elif message.role == "tool" or message.role == "ipython" %}
82
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
83
+ {%- if message.content is mapping or message.content is iterable %}
84
+ {{- message.content | tojson }}
85
+ {%- else %}
86
+ {{- message.content }}
87
+ {%- endif %}
88
+ {{- "<|eot_id|>" }}
89
+ {%- endif %}
90
+ {%- endfor %}
91
+ {%- if add_generation_prompt %}
92
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
93
+ {%- endif %}
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz16/global_step_64/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:490556f05c9dde78359c95352fe92257a54cd3ea48237de3952bc127422cb41e
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_128/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5831328a561d59acb25dc12c7bed3f6b77f018fa8169f3424327667121f2bb
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_192/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc40fcd37e9c358a37922c0bf0396df93d1b3f08e99dc804b62e37feac97f33
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_256/data.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6da73a44113782a19ab6ca7bb319748990791ecaca9196a51de48982f779a6
3
+ size 1947
Llama-3.2-3B-Instruct-polaris-GRPO--bsz256/global_step_320/actor_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920