Lyaaaaaaaaaaaaaaa commited on
Commit
acc854f
1 Parent(s): df6fe51

Initial commit

Browse files
Files changed (45) hide show
  1. README.md +1 -3
  2. config.json +30 -0
  3. generation_config.json +7 -0
  4. pytorch_model-00001-of-00037.bin +3 -0
  5. pytorch_model-00002-of-00037.bin +3 -0
  6. pytorch_model-00003-of-00037.bin +3 -0
  7. pytorch_model-00004-of-00037.bin +3 -0
  8. pytorch_model-00005-of-00037.bin +3 -0
  9. pytorch_model-00006-of-00037.bin +3 -0
  10. pytorch_model-00007-of-00037.bin +3 -0
  11. pytorch_model-00008-of-00037.bin +3 -0
  12. pytorch_model-00009-of-00037.bin +3 -0
  13. pytorch_model-00010-of-00037.bin +3 -0
  14. pytorch_model-00011-of-00037.bin +3 -0
  15. pytorch_model-00012-of-00037.bin +3 -0
  16. pytorch_model-00013-of-00037.bin +3 -0
  17. pytorch_model-00014-of-00037.bin +3 -0
  18. pytorch_model-00015-of-00037.bin +3 -0
  19. pytorch_model-00016-of-00037.bin +3 -0
  20. pytorch_model-00017-of-00037.bin +3 -0
  21. pytorch_model-00018-of-00037.bin +3 -0
  22. pytorch_model-00019-of-00037.bin +3 -0
  23. pytorch_model-00020-of-00037.bin +3 -0
  24. pytorch_model-00021-of-00037.bin +3 -0
  25. pytorch_model-00022-of-00037.bin +3 -0
  26. pytorch_model-00023-of-00037.bin +3 -0
  27. pytorch_model-00024-of-00037.bin +3 -0
  28. pytorch_model-00025-of-00037.bin +3 -0
  29. pytorch_model-00026-of-00037.bin +3 -0
  30. pytorch_model-00027-of-00037.bin +3 -0
  31. pytorch_model-00028-of-00037.bin +3 -0
  32. pytorch_model-00029-of-00037.bin +3 -0
  33. pytorch_model-00030-of-00037.bin +3 -0
  34. pytorch_model-00031-of-00037.bin +3 -0
  35. pytorch_model-00032-of-00037.bin +3 -0
  36. pytorch_model-00033-of-00037.bin +3 -0
  37. pytorch_model-00034-of-00037.bin +3 -0
  38. pytorch_model-00035-of-00037.bin +3 -0
  39. pytorch_model-00036-of-00037.bin +3 -0
  40. pytorch_model-00037-of-00037.bin +3 -0
  41. pytorch_model.bin.index.json +244 -0
  42. special_tokens_map.json +23 -0
  43. tokenizer.json +0 -0
  44. tokenizer.model +3 -0
  45. tokenizer_config.json +42 -0
README.md CHANGED
@@ -1,3 +1 @@
1
- ---
2
- license: mit
3
- ---
 
1
+ Sharded version of the original https://huggingface.co/openlm-research/open_llama_3b_v2
 
 
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openlm-research/open_llama_3b_v2",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3200,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8640,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 26,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.44.0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.0"
7
+ }
pytorch_model-00001-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a9080ec448726ec86f03d31cdfa697858c6f84eb56193de9198ce06d3fc343
3
+ size 204801413
pytorch_model-00002-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07eeaf684bd495d995bbb21f80327b36039cbaa0cff81a4055bfc19b2139c71f
3
+ size 192514970
pytorch_model-00003-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98dfb0759f98c47794e48630a452b3973f5d01708e525e484162e05b3997819a
3
+ size 192528380
pytorch_model-00004-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:334bd33a9cef2748b0fb0b2321cca5c0d3c6515b0e39fe0205df7cd29eb69310
3
+ size 192528380
pytorch_model-00005-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d8a14afd3aed5af45de3546613cb342db4c87d39ccddc9686706a93fbc3b2e
3
+ size 186383770
pytorch_model-00006-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0cdcaa6e62229b2d738867f6e4c602d6dc51f69e6fcde330e53d1b0903573d
3
+ size 172034697
pytorch_model-00007-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ada67ea5703e541f87b6afeffabb6b8821b22d8350697087fef403b3831e808
3
+ size 192528380
pytorch_model-00008-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8bba0cb4b804a18766cd32d0673d6b47562ab0a22d9006b1e766d64bb34454
3
+ size 192528380
pytorch_model-00009-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16dd7bdec9d0dd367d4a666402635059f6e8f080d47177661525be35daf3c445
3
+ size 186383770
pytorch_model-00010-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0933eff76436c8ad19ebbc4f447d139d3e92c96502be3b673cb4edf266edbc0c
3
+ size 172034697
pytorch_model-00011-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb01d3f6a7b6287f5ebd9613316d80abc9133c59db77ecf6a92c9a5da29a7bca
3
+ size 192528380
pytorch_model-00012-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7457ce07828127fa9cd289a00d4933ea6149d7b82887a5c52f88cfeb3da282c
3
+ size 192528380
pytorch_model-00013-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee3b9ebf93e7cf29fd6f59f4a6c4c600d32d7fc2900339e792a931b11d7a2e0
3
+ size 186383770
pytorch_model-00014-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b77519ea6f9af09224f5ecd85f000e66c2579b38fd71530a82449ef508965b
3
+ size 172034697
pytorch_model-00015-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c971925210bdbd504ae8630d91e69004a8fae02fdf9fa8580812a57910d8537b
3
+ size 192528380
pytorch_model-00016-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2868f2354b1e0ae7e708caf36f9cbd9f856437812b1950dc19bc51a523c7bf
3
+ size 192528380
pytorch_model-00017-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66980ee3ce10419f1e3bba150093f215d89ae14024f389eaf4f09a38ae4c70f6
3
+ size 186383770
pytorch_model-00018-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db1e1a262d88319c9f9d05115d16cdd16073f9f8aa0f2de6cb5d902c2191156d
3
+ size 172034697
pytorch_model-00019-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0746ab6a850d4b23b89c2318bd4c8a8db837602425a99f282a0f3052dc7c091b
3
+ size 192528380
pytorch_model-00020-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de33b0502c3a0b9eb9a4ee13c05a3b46714585db3d5ffcbfd5480fa574e28ce7
3
+ size 192528380
pytorch_model-00021-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521ffc0072a31cf4a0799000233a0b1915a0c64199b107701656547b1804978b
3
+ size 186383770
pytorch_model-00022-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1364feff19d6b25a87148d46e97bdeea9b55eb3192eb285f5f73ab371d2b17
3
+ size 172034697
pytorch_model-00023-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e426a364e0d6148e5ef0ffbf0497f08fe019550543aca38b917e8d2b8a60481d
3
+ size 192528380
pytorch_model-00024-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c221fc62f2273675773e4e18ece8fd06136d89f783749e5656711c934d8eb3
3
+ size 192528380
pytorch_model-00025-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352dfcb61d578d72dc63f7c4378b9dee83ab37dd313c97dc73d33ddbce70f15f
3
+ size 186383770
pytorch_model-00026-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc3e4b40cbfdbc641940ac2a9b08e4b8bf8903ebd0486d8ae1a8f1d7d54dbdc
3
+ size 172034697
pytorch_model-00027-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a9d6f19d765f77dd2661ce2c3e4e93c2f43f63ad273eec2e6057954a300973
3
+ size 192528380
pytorch_model-00028-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64741fceeef3307c9ee2663b8c7f9b13dfb8c57ccd4ae7af3e5ed06ade5024c1
3
+ size 192528380
pytorch_model-00029-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f23b4ca4e90d0f67042e3d086733f419e645662c9d5b799d6cf8ab068f5ba6c
3
+ size 186383770
pytorch_model-00030-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c56890209a14b206350d191bc6d98ec6303466317a2ca896502f62886bc238d
3
+ size 172034697
pytorch_model-00031-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990c295654542ac8c07f687119366a9afcf0986d00a3253846ad3065eb2550ec
3
+ size 192528380
pytorch_model-00032-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4b846f7d8a425e9c2a3e6f0cf6d1da3dc135691ca6b227d1bc1e91f5cc801f
3
+ size 192528380
pytorch_model-00033-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea893f23490ac251b732dc2d6bffea0bbec98e2795b7850b197191876e85a38
3
+ size 186383770
pytorch_model-00034-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d64564fd686ba1bfcb82e6f4049854716bed969b3e8e6841bb3c265666b3c85
3
+ size 172034697
pytorch_model-00035-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be5b454d5819f2922b2c3bccc066dd908f29f8bf9e506bf86c2c07ca973373c7
3
+ size 192528380
pytorch_model-00036-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90bfe7b038aac4ce30683b1abd3b11be7f1ae688a6c2ab064397ca658c639905
3
+ size 204801413
pytorch_model-00037-of-00037.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f3438f7a02ebb1840bb39379b13153fb29d2cb26339566d86e9fc06b1e79284
3
+ size 110613833
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6852947200
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00036-of-00037.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00037.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00003-of-00037.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00003-of-00037.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00037.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00037.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00003-of-00037.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00037.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00037.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00037.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00037.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00037.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00004-of-00037.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00037.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00004-of-00037.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00037.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00037.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00037.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00037.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00037.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00016-of-00037.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00016-of-00037.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00015-of-00037.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00016-of-00037.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00016-of-00037.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00015-of-00037.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00015-of-00037.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00015-of-00037.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00015-of-00037.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00017-of-00037.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00017-of-00037.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00017-of-00037.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00017-of-00037.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00017-of-00037.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00016-of-00037.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00016-of-00037.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00016-of-00037.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00016-of-00037.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00019-of-00037.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00019-of-00037.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00018-of-00037.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00018-of-00037.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00019-of-00037.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00018-of-00037.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00018-of-00037.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00017-of-00037.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00018-of-00037.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00020-of-00037.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00020-of-00037.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00019-of-00037.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00020-of-00037.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00020-of-00037.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00019-of-00037.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00019-of-00037.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00019-of-00037.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00019-of-00037.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00021-of-00037.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00021-of-00037.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00021-of-00037.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00021-of-00037.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00021-of-00037.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00020-of-00037.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00020-of-00037.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00020-of-00037.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00020-of-00037.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00023-of-00037.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00023-of-00037.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00022-of-00037.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00022-of-00037.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00023-of-00037.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00022-of-00037.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00022-of-00037.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00021-of-00037.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00022-of-00037.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00024-of-00037.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00024-of-00037.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00023-of-00037.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00024-of-00037.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00024-of-00037.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00023-of-00037.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00023-of-00037.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00023-of-00037.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00023-of-00037.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00025-of-00037.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00025-of-00037.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00025-of-00037.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00025-of-00037.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00025-of-00037.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00024-of-00037.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00024-of-00037.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00024-of-00037.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00024-of-00037.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00027-of-00037.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00027-of-00037.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00026-of-00037.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00026-of-00037.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00027-of-00037.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00026-of-00037.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00026-of-00037.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00025-of-00037.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00026-of-00037.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00028-of-00037.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00028-of-00037.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00027-of-00037.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00028-of-00037.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00028-of-00037.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00027-of-00037.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00027-of-00037.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00027-of-00037.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00027-of-00037.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00037.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00037.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00005-of-00037.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00005-of-00037.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00037.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00004-of-00037.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00037.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00004-of-00037.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00037.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00029-of-00037.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00029-of-00037.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00029-of-00037.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00029-of-00037.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00029-of-00037.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00028-of-00037.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00028-of-00037.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00028-of-00037.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00028-of-00037.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00031-of-00037.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00031-of-00037.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00030-of-00037.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00030-of-00037.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00031-of-00037.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00030-of-00037.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00030-of-00037.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00029-of-00037.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00030-of-00037.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00032-of-00037.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00032-of-00037.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00031-of-00037.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00032-of-00037.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00032-of-00037.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00031-of-00037.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00031-of-00037.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00031-of-00037.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00031-of-00037.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00033-of-00037.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00033-of-00037.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00033-of-00037.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00033-of-00037.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00033-of-00037.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00032-of-00037.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00032-of-00037.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00032-of-00037.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00032-of-00037.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00035-of-00037.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00035-of-00037.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00034-of-00037.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00034-of-00037.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00035-of-00037.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00034-of-00037.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00034-of-00037.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00033-of-00037.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00034-of-00037.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00037-of-00037.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00037-of-00037.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00035-of-00037.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00037-of-00037.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00037-of-00037.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00035-of-00037.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00035-of-00037.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00035-of-00037.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00035-of-00037.bin",
179
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00007-of-00037.bin",
180
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00007-of-00037.bin",
181
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00006-of-00037.bin",
182
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00006-of-00037.bin",
183
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00007-of-00037.bin",
184
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00006-of-00037.bin",
185
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00006-of-00037.bin",
186
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00005-of-00037.bin",
187
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00006-of-00037.bin",
188
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00008-of-00037.bin",
189
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00008-of-00037.bin",
190
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00007-of-00037.bin",
191
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00008-of-00037.bin",
192
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00008-of-00037.bin",
193
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00007-of-00037.bin",
194
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00007-of-00037.bin",
195
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00007-of-00037.bin",
196
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00007-of-00037.bin",
197
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00009-of-00037.bin",
198
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00009-of-00037.bin",
199
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00009-of-00037.bin",
200
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00009-of-00037.bin",
201
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00009-of-00037.bin",
202
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00008-of-00037.bin",
203
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00008-of-00037.bin",
204
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00008-of-00037.bin",
205
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00008-of-00037.bin",
206
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00011-of-00037.bin",
207
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00011-of-00037.bin",
208
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00010-of-00037.bin",
209
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00010-of-00037.bin",
210
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00011-of-00037.bin",
211
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00010-of-00037.bin",
212
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00010-of-00037.bin",
213
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00009-of-00037.bin",
214
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00010-of-00037.bin",
215
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00012-of-00037.bin",
216
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00012-of-00037.bin",
217
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00011-of-00037.bin",
218
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00012-of-00037.bin",
219
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00012-of-00037.bin",
220
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00011-of-00037.bin",
221
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00011-of-00037.bin",
222
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00011-of-00037.bin",
223
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00011-of-00037.bin",
224
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00013-of-00037.bin",
225
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00013-of-00037.bin",
226
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00013-of-00037.bin",
227
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00013-of-00037.bin",
228
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00013-of-00037.bin",
229
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00012-of-00037.bin",
230
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00012-of-00037.bin",
231
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00012-of-00037.bin",
232
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00012-of-00037.bin",
233
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00015-of-00037.bin",
234
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00015-of-00037.bin",
235
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00014-of-00037.bin",
236
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00014-of-00037.bin",
237
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00015-of-00037.bin",
238
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00014-of-00037.bin",
239
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00014-of-00037.bin",
240
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00013-of-00037.bin",
241
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00014-of-00037.bin",
242
+ "model.norm.weight": "pytorch_model-00037-of-00037.bin"
243
+ }
244
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
3
+ size 511574
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 2048,
36
+ "pad_token": null,
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }