Upload Kimi K2.5 BF16 safetensors (converted from native INT4)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+license: other
+license_name: modified-mit
+license_link: https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE
+base_model: moonshotai/Kimi-K2.5
+tags:
+  - kimi
+  - moe
+  - bf16
+---
+
+# Kimi K2.5 — BF16 Safetensors
+
+BF16 (bfloat16) conversion of [Moonshot AI's Kimi K2.5](https://huggingface.co/moonshotai/Kimi-K2.5).
+
+Converted from the official native INT4 weights so that LlamaFactory + KTransformers
+can run LoRA SFT directly without a per-run conversion step.
+
+| Spec | Value |
+|------|-------|
+| Source | `moonshotai/Kimi-K2.5` |
+| Format | safetensors (BF16) |
+| Shards | 64 |
+| Total size | ~1913 GB |
+| Architecture | MoE — 1T total, 32B active |
+| Context | 256K tokens |
+
+## Usage with LlamaFactory + KTransformers
+
+```yaml
+model_name_or_path: ananayarora/Kimi-K2.5-BF16
+stage: sft
+finetuning_type: lora
+bf16: true
+use_kt: true
+```
+
+## License
+
+Same as the base model: [Modified MIT](https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE).

config.json

@@ -0,0 +1,193 @@
+{
+  "architectures": [
+    "KimiK25ForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_kimi_k25.KimiK25Config",
+    "AutoModel": "modeling_kimi_k25.KimiK25ForConditionalGeneration",
+    "AutoModelForCausalLM": "modeling_kimi_k25.KimiK25ForConditionalGeneration"
+  },
+  "bos_token_id": 163584,
+  "dtype": "bfloat16",
+  "eos_token_id": 163585,
+  "ignore_index": -100,
+  "media_placeholder_token_id": 163605,
+  "model_type": "kimi_k25",
+  "pad_token_id": 163839,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "DeepseekV3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration_deepseek.DeepseekV3Config",
+      "AutoModel": "modeling_deepseek.DeepseekV3Model",
+      "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
+    },
+    "aux_loss_alpha": 0.001,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 163584,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dtype": "bfloat16",
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 163585,
+    "ep_size": 1,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "first_k_dense_replace": 1,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18432,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "kv_lora_rank": 512,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 262144,
+    "min_length": 0,
+    "model_type": "kimi_k2",
+    "moe_intermediate_size": 2048,
+    "moe_layer_freq": 1,
+    "n_group": 1,
+    "n_routed_experts": 384,
+    "n_shared_experts": 1,
+    "no_repeat_ngram_size": 0,
+    "norm_topk_prob": true,
+    "num_attention_heads": 64,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 61,
+    "num_key_value_heads": 64,
+    "num_nextn_predict_layers": 0,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 163839,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "q_lora_rank": 1536,
+    "qk_nope_head_dim": 128,
+    "qk_rope_head_dim": 64,
+    "quantization_config": {
+      "config_groups": {
+        "group_0": {
+          "input_activations": null,
+          "output_activations": null,
+          "targets": [
+            "Linear"
+          ],
+          "weights": {
+            "actorder": null,
+            "block_structure": null,
+            "dynamic": false,
+            "group_size": 32,
+            "num_bits": 4,
+            "observer": "minmax",
+            "observer_kwargs": {},
+            "strategy": "group",
+            "symmetric": true,
+            "type": "int"
+          }
+        }
+      },
+      "format": "pack-quantized",
+      "ignore": [
+        "lm_head",
+        "re:.*self_attn.*",
+        "re:.*shared_experts.*",
+        "re:.*mlp\\.(gate|up|gate_up|down)_proj.*"
+      ],
+      "kv_cache_scheme": null,
+      "quant_method": "compressed-tensors",
+      "quantization_status": "compressed"
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "beta_fast": 32.0,
+      "beta_slow": 1.0,
+      "factor": 64.0,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "original_max_position_embeddings": 4096,
+      "type": "yarn"
+    },
+    "rope_theta": 50000.0,
+    "routed_scaling_factor": 2.827,
+    "scoring_func": "sigmoid",
+    "sep_token_id": null,
+    "seq_aux": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "topk_group": 1,
+    "topk_method": "noaux_tc",
+    "torchscript": false,
+    "transformers_version": "4.56.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "v_head_dim": 128,
+    "vocab_size": 163840,
+    "torch_dtype": "bfloat16"
+  },
+  "tie_word_embeddings": false,
+  "use_unified_vision_chunk": true,
+  "video_placeholder": "<|kimi_k25_video_placeholder|>",
+  "vision_config": {
+    "_attn_implementation": "flash_attention_2",
+    "init_pos_emb_height": 64,
+    "init_pos_emb_time": 4,
+    "init_pos_emb_width": 64,
+    "merge_kernel_size": [
+      2,
+      2
+    ],
+    "merge_type": "sd2_tpool",
+    "mm_hidden_size": 1152,
+    "mm_projector_type": "patchmerger",
+    "patch_size": 14,
+    "pos_emb_type": "divided_fixed",
+    "projector_hidden_act": "gelu",
+    "projector_ln_eps": 1e-05,
+    "text_hidden_size": 7168,
+    "video_attn_type": "spatial_temporal",
+    "vt_hidden_size": 1152,
+    "vt_intermediate_size": 4304,
+    "vt_num_attention_heads": 16,
+    "vt_num_hidden_layers": 27
+  }
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "max_length": 262144,
+  "eos_token_id": 163586
+}

model-00001-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18daf53a15070b9c70d8bb63420dbd39764af9118af67982eeb60749f5453233
+size 995001888

model-00002-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9535c797e8db2572793a99c710b9ec78c2645bb4d6858e066392571a02a9ce6a
+size 34118896048

model-00003-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b305507ccc809fb9992a13dcafd7c3281d3352c6b8043dfb38a01bad85aab2c3
+size 34118896048

model-00004-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775c4915029fad7c369390cef5cbdfc086cc1884b549b5ab8eb2fa3cd7874245
+size 34118896048

model-00005-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30145eb7bf1084dc20e0c2e20650f86753a3b7e6a2df2915914a48d6abbb5d8
+size 34118896048

model-00006-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d65c3b63e9d41e2fc0a307df8e893ba134855c1e2815e687f0db6dd12ceddfe
+size 34118896048

model-00007-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b322e12517022dac25ba1b8637cb99665502c13304c3a9b141c2dcce726ff739
+size 34118896048

model-00008-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9681801be93a11b40b7be1c6f065f01e10b38d66b3e586b5ad7742a78ff44844
+size 34118896048

model-00009-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5de2bba6cbce883edd05b434394a8eca9e868a32c4090666a3792c2db0f9ead9
+size 34118896048

model-00010-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4cfa8b734784fa2057b85dd0792a070333d8051396ae61e63f8e5861fa8fbc
+size 34118896048

model-00011-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98a5ded58360c2fc93b692153952d0a2e82d60d72f37eebcbabf1a2cde8f9d1f
+size 34118897216

model-00012-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6accb526370e3185dc4d9989c8ba0bc4366db4a29f3b24a389c286dc8012d08
+size 34118897216

model-00013-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be50ab4f5ddb7dd616d148359752191863f16c7b50e3a35012c1c3bd6a75ee1
+size 34118897216

model-00014-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:259387fa691a603a2a877752f42d047e245e389c09e3f4df0e8580d3ed85525f
+size 34118897216

model-00015-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baefc0d8d06536e82481966d5d82589ffe530850241306b944092bd7182ed484
+size 34118897216

model-00016-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13200caf01c1211f1ced5030208255e15cde48d41d0d664941072d7c830729f6
+size 34118897216

model-00017-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec76dd39e3c9b13d1c958d5248f8316b3afd30139cb4090435d6597e9ae9583
+size 34118897216

model-00018-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3420fb700996d5079f30d7041e1e5c91a02d3d2d5080e5dcbe4b1abc6bd239d4
+size 34118897216

model-00019-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64309d1919fc10937fd0c0719a0cbab2383c3db8b19f97e06eeaeb8c57b84b77
+size 34118897216

model-00020-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e501987568c9391bc1c2af3390b7b6e4b160842fad38b52e17d1dff9fae3c309
+size 34118897216

model-00021-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8f799ebc880bf48951d9c3d81bbee3bd0c2993ccca70e8d6ab3e2f719346086
+size 34118897216

model-00022-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f228bcd96b8988f8eae156797e6f1ce5342b6159a2dcec55187226c09b2211
+size 34118897216

model-00023-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10147c74a915ae9ab345d638ecf9c4f90468335ecc0ae5a61907289bfe2f051
+size 34118897216

model-00024-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed0ba4e761ce4e65beb3178b71465805793bf6a16120980c9c52b1fe2ab3e84
+size 34118897216

model-00025-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7893fe1dc30900b129878e3302cc9e9362417e9cbb70459888ad8e5f9aa3ed
+size 34118897216

model-00026-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2cb0a60c6b6515193a2cf2b23fc81181985847af93fbdbb16eb5b8cd432572
+size 34118897216

model-00027-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064d63ab70d3f809baf04155d08266ff54da9d6f5720a8799c76b920ad477622
+size 34118897216

model-00028-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c3f65ff8c0086dd045e34c5ce60e3a70d046bdf47dd76692a2989286d9055e
+size 34118897216

model-00029-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfd6520fe0e375559e9573e28aa00259c2154c8dc50f45f2f044cf902a568fbb
+size 34118897216

model-00030-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4f185271738370d7602b91dc849ca9fb27fa7d11eb67d21e519830e9d7505d
+size 34118897216

model-00031-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28f08ef93004176271e95ab6a882cc067253281a035724837d98ddf79fcf0a7
+size 34118897216

model-00032-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee566725f7348f501af363b367a962a0a95e5965ae4ee52213f0c024a3a0235
+size 34118897216

model-00033-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c436d9f96ae92991769f99f81e8f37ad6c3364c21bbfdd828307b913dc6cd0
+size 34118897216

model-00034-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38493055f5d90fec9270697e7fcb37527547a1f52e1f03502e83053e4e6f9193
+size 34118897216

model-00035-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ee30b08eddc5997cd269cab90524b078eabfa835e0094648fe7ae81b68ff3a
+size 34118897216

model-00036-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f0a120d515b0fd4d848517c0cd5ed9e22e66ca6571d207e88a441f299d0d1f
+size 34118897216

model-00037-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0415bf74c71c1648b73a823e9902468e9f7eb7117e730db0a31761f49b9af782
+size 34118897216

model-00038-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ac3e771279ca7e04a11f0cd34019e126d50ddbc9b484e4b91226619e35a8a1
+size 34118897216

model-00039-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dcba7989997f258c9c84824273add6ae03a118e4f43490eba76676d8463b1ec
+size 34118897216

model-00040-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336dc37932616c9d80370ba63036196fc45ab36064d99d1ebb16c495826fd5a9
+size 34118897216

model-00041-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac59ce7b12dd43be50236c8a6e8750d47c670aecb260f13be48e5e700201795
+size 34118897216

model-00042-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7f9d73e33ee81c53ebaf6374f3a5415f4b3ff471cf36d56b5689433bfc2025
+size 34118897216

model-00043-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341fcaa3825623022ca6c7e613e97b308013e430a98d94d9f4d3260944cae44e
+size 34118897216

model-00044-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a787893f3e11861873b63e638954cb37c232ca880640fc4d0e9bea098ae4e69
+size 34118897216

model-00045-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba50d0972dd3c86f8d33b95ba6a0c0dd41d30f53e2a6670f14d4260fd48f9af1
+size 34118897216

model-00046-of-000064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd642d9a704c0016b0c33894b7c84987fb75fe21460d49b2e421eb6491faa21
+size 34118897216