Hugging Face's logo

CuriousCat29
/
l3-stack-mocha-2

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Model card Files
xet
Community
CuriousCat29 commited on
Commit
2446071
·
verified ·
1 Parent(s): 79b2d22

Upload folder using huggingface_hub

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 +1 -0
  2. README.md +57 -0
  3. config.json +39 -0
  4. mergekit_config.yml +26 -0
  5. model-00001-of-00050.safetensors +3 -0
  6. model-00002-of-00050.safetensors +3 -0
  7. model-00003-of-00050.safetensors +3 -0
  8. model-00004-of-00050.safetensors +3 -0
  9. model-00005-of-00050.safetensors +3 -0
  10. model-00006-of-00050.safetensors +3 -0
  11. model-00007-of-00050.safetensors +3 -0
  12. model-00008-of-00050.safetensors +3 -0
  13. model-00009-of-00050.safetensors +3 -0
  14. model-00010-of-00050.safetensors +3 -0
  15. model-00011-of-00050.safetensors +3 -0
  16. model-00012-of-00050.safetensors +3 -0
  17. model-00013-of-00050.safetensors +3 -0
  18. model-00014-of-00050.safetensors +3 -0
  19. model-00015-of-00050.safetensors +3 -0
  20. model-00016-of-00050.safetensors +3 -0
  21. model-00017-of-00050.safetensors +3 -0
  22. model-00018-of-00050.safetensors +3 -0
  23. model-00019-of-00050.safetensors +3 -0
  24. model-00020-of-00050.safetensors +3 -0
  25. model-00021-of-00050.safetensors +3 -0
  26. model-00022-of-00050.safetensors +3 -0
  27. model-00023-of-00050.safetensors +3 -0
  28. model-00024-of-00050.safetensors +3 -0
  29. model-00025-of-00050.safetensors +3 -0
  30. model-00026-of-00050.safetensors +3 -0
  31. model-00027-of-00050.safetensors +3 -0
  32. model-00028-of-00050.safetensors +3 -0
  33. model-00029-of-00050.safetensors +3 -0
  34. model-00030-of-00050.safetensors +3 -0
  35. model-00031-of-00050.safetensors +3 -0
  36. model-00032-of-00050.safetensors +3 -0
  37. model-00033-of-00050.safetensors +3 -0
  38. model-00034-of-00050.safetensors +3 -0
  39. model-00035-of-00050.safetensors +3 -0
  40. model-00036-of-00050.safetensors +3 -0
  41. model-00037-of-00050.safetensors +3 -0
  42. model-00038-of-00050.safetensors +3 -0
  43. model-00039-of-00050.safetensors +3 -0
  44. model-00040-of-00050.safetensors +3 -0
  45. model-00041-of-00050.safetensors +3 -0
  46. model-00042-of-00050.safetensors +3 -0
  47. model-00043-of-00050.safetensors +3 -0
  48. model-00044-of-00050.safetensors +3 -0
  49. model-00045-of-00050.safetensors +3 -0
  50. model-00046-of-00050.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
4
+ - TheDrummer/Fallen-Llama-3.3-70B-v1
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # merged
12
+
13
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
14
+
15
+ ## Merge Details
16
+ ### Merge Method
17
+
18
+ This model was merged using the Passthrough merge method.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * [Doctor-Shotgun/L3.3-70B-Magnum-v4-SE](https://huggingface.co/Doctor-Shotgun/L3.3-70B-Magnum-v4-SE)
24
+ * [TheDrummer/Fallen-Llama-3.3-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-70B-v1)
25
+
26
+ ### Configuration
27
+
28
+ The following YAML configuration was used to produce this model:
29
+
30
+ ```yaml
31
+ dtype: bfloat16
32
+ merge_method: passthrough
33
+ modules:
34
+ default:
35
+ slices:
36
+ - sources:
37
+ - layer_range: [0, 20]
38
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
39
+ - sources:
40
+ - layer_range: [10, 30]
41
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
42
+ - sources:
43
+ - layer_range: [20, 40]
44
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
45
+ - sources:
46
+ - layer_range: [30, 50]
47
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
48
+ - sources:
49
+ - layer_range: [40, 60]
50
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
51
+ - sources:
52
+ - layer_range: [50, 70]
53
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
54
+ - sources:
55
+ - layer_range: [60, 80]
56
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
57
+ ```
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 8192,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 28672,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 64,
22
+ "num_hidden_layers": 140,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.53.0",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ modules:
4
+ default:
5
+ slices:
6
+ - sources:
7
+ - layer_range: [0, 20]
8
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
9
+ - sources:
10
+ - layer_range: [10, 30]
11
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
12
+ - sources:
13
+ - layer_range: [20, 40]
14
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
15
+ - sources:
16
+ - layer_range: [30, 50]
17
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
18
+ - sources:
19
+ - layer_range: [40, 60]
20
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
21
+ - sources:
22
+ - layer_range: [50, 70]
23
+ model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
24
+ - sources:
25
+ - layer_range: [60, 80]
26
+ model: TheDrummer/Fallen-Llama-3.3-70B-v1
model-00001-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985f23c68602f9dcd77c92f0049127d865c0e4fb02dfac529b08310ef06e9e0f
3
+ size 4672471504
model-00002-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3e4e6536fa129bb68b906f2acffd5adb2dcda5004d83f37330560f85e79231
3
+ size 4831922704
model-00003-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34cd210934d16aeee43cccc4a722241a0e45f1b775ee89a6c4e0a46b863bcb2
3
+ size 4966190768
model-00004-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1c39bc0721309c375fe60fc25f54697c15bf7aca80667ec17fd7e607b5706b
3
+ size 4831906224
model-00005-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc4763d44bbe233a46035071c6160c8db6e2d6d661c5a4cdc4ae11e055d95ba
3
+ size 4999711736
model-00006-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:566bcd06968440b25f2041f51a6edb9fe9de22049399bc4c8194702e0fbcf9ad
3
+ size 4798385256
model-00007-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2931e0450035d1c45702e840695526ad5d1b91106c423fb44e1b2b17aa5972d8
3
+ size 4831906216
model-00008-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac1bf90ae842da254b2149b38dff591ed3a0fd7fb6312bde38d8f3ff08a0ecb
3
+ size 4966190760
model-00009-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf7bdbe8c9e59702a294cd2a17a459a668fceb76a9a13d7c14d6323be6c9ae0
3
+ size 4664167408
model-00010-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f48d8c4cce70d365334b59275235650c8486e63274e4c8c30a5c5dcbfa3cc2
3
+ size 4831906224
model-00011-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ace9f8e9f1b4c4624af0e9d946305d7c6f4aa38c8c367600358057405c9dfb
3
+ size 4999711736
model-00012-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbafdb169e9bc9f0a84b11487a006e4f1206138cd165581b946bae69fea75f3
3
+ size 4798385256
model-00013-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31bbf4e8110390b93a846bfe351e685db9d7e94b9355c13bf8c9a6abb7d14b52
3
+ size 4831906216
model-00014-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f04990950547023c8cf3beedc62933cbdc81e7bb8675141cb1453ed753ca2e2
3
+ size 4966190760
model-00015-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a0ca099dfe261b547b90746335cf95a20478a565078af1dd32bba90c09d305
3
+ size 4831906224
model-00016-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254a43eca3ce92b56df1ea88d07c35dc53d37f2ecf1e92e46dafd982b507110a
3
+ size 4966174264
model-00017-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc10a5144e3491f6bb854a446a50bd66e031fb2daad50e53d40d10807cfadbb
3
+ size 4966140568
model-00018-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f409317ff8ec4368171d1b9ea1631ae863c2db64177057cf619ae2c21c9c94c
3
+ size 4999711720
model-00019-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bff6f87a0f434047255a0076404e6ec1f82aa328671c77c3aa5df337eb5e864
3
+ size 4999711736
model-00020-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e28e2d1382ea848660f7a38ec6d08f12a79fe704aa9a40d9121caa63de86355
3
+ size 4798385256
model-00021-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3407c26b84eb8d4e35628ff543892e3bc9f6b9049a4b69126d671824ea3db745
3
+ size 4831906216
model-00022-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fc5e77184e347c6132c28aa875af51c15ac7bd7d95bcdce4c257ea5e7784f2
3
+ size 4966190760
model-00023-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f3e67db0cf381bd84aefc342b062e582b8e8510bbfcb40c1d48d56ee286fbc
3
+ size 4831906224
model-00024-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266f992ef72546842d3f9578662751c9c9c662a1e25b83521264b43a188d3505
3
+ size 4664167400
model-00025-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3a5a5b980e1cccb6c516e2eb3f41c0ec5ebd7b20c09dbe8df6b6c66b73b4b16
3
+ size 4999711736
model-00026-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12af4bad84a456825b607e3afa55d06bd63bba0ec09625b5c92fbf93e5b5451
3
+ size 4798385256
model-00027-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f35b2ca344b5e815384efe0176fb7796f2620f64098dc32ba5eba6a98b5bd9
3
+ size 4831906216
model-00028-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b0088a280db6a2c50bebf0c76bc6ea93515f501342a07d061a16598b934087
3
+ size 4966190760
model-00029-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3972d4273dfeb4e717fbd691ac20f0de68b5c897899a58a64a508131334e7b1
3
+ size 4831906224
model-00030-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd1000a816e9515f56181c821e7a5c9cf8a6dd2b9b3a90cbd9ad9bd3efec2ee
3
+ size 4966190768
model-00031-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf371600689352acf947c549cf857f122db8b3a235b99271210c66c584460c6f
3
+ size 4982901392
model-00032-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9adbf77d7036bac70f7327b6586bfe6356ecf89b5746c359a55c21f813dc10
3
+ size 4982934392
model-00033-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65d0f2b512ec08add6ec7022f748063b7a25e4357a7d91fd81607141ae7796a9
3
+ size 4999711752
model-00034-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdba4b8c64fd184121facb9c86c05972284f515644153f7dfce6cf250a3320f1
3
+ size 4798385264
model-00035-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45bd737fd4bcc9c74e1266b6bb7dab7b5c3eb4c78ec0fc10d6b367f2b1d4b2b4
3
+ size 4831906232
model-00036-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94723fd9a9c0aab982cf419cd81a569d7e4142a4056e37901e471037f0b68596
3
+ size 4966190784
model-00037-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda86d13b294b6b175873138a0023fddd955097ea76fa29c5a6fabe48a232eb5
3
+ size 4831906232
model-00038-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdb45f492afe4408f51d9f0986ca2207829e3992b7efbd3ba9786cacf9bb3bf
3
+ size 4966174288
model-00039-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f26689a36e74ef2cc074895057845f387cb85371c7da533ff996e194589abe2
3
+ size 4966140568
model-00040-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a234b6df0f7ce898b2d6491420fdac05f0249611fe70514b066dd3b28b438efe
3
+ size 4999711752
model-00041-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a50518cb3fbc9299b1b2c7768b56b800a4c88c17140fe745817683fd3e36457
3
+ size 4999711760
model-00042-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e2dbafba18a183670453ef3220d7c268ee90cb6b8b5f7bbebde7024dbdd544
3
+ size 4798385280
model-00043-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79025c441347ada806c5ab87b12f1f19019e3af97b3a961698d8225016a993cf
3
+ size 4831906240
model-00044-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a391df627c02c26025a73c4f1d7f3ffe47df6d8bf08d3b0eb4a2215ef918fe73
3
+ size 4966190792
model-00045-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6933cf1d8711b92dc1dc9199326a9f54a6766acd91b0744223c3de942f9ef9d0
3
+ size 4831906240
model-00046-of-00050.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca5e0f3ebe8757407f5d5708d3ac6cf66ead4dea36dfe654a959be52a3c5a042
3
+ size 4966174288