Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+base_model:
+- mkurman/LiquidAI-LFM2.5-350M-SYNTH
+- MihaiPopa-1/LFM2.5-350M-heretic
+- appvoid/palmer-005-core
+- squ11z1/claude-oss-350m
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [MihaiPopa-1/LFM2.5-350M-heretic](https://huggingface.co/MihaiPopa-1/LFM2.5-350M-heretic) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [mkurman/LiquidAI-LFM2.5-350M-SYNTH](https://huggingface.co/mkurman/LiquidAI-LFM2.5-350M-SYNTH)
+* [appvoid/palmer-005-core](https://huggingface.co/appvoid/palmer-005-core)
+* [squ11z1/claude-oss-350m](https://huggingface.co/squ11z1/claude-oss-350m)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: dare_ties
+base_model: MihaiPopa-1/LFM2.5-350M-heretic
+dtype: bfloat16
+
+parameters:
+  normalize: false
+  int8_mask: true
+
+models:
+  # slot_1_strongest
+  - model: mkurman/LiquidAI-LFM2.5-350M-SYNTH
+    parameters:
+      weight: 0.28
+      density: 0.38
+
+  # slot_2_medium
+  - model: squ11z1/claude-oss-350m
+    parameters:
+      weight: 0.22
+      density: 0.34
+
+  # slot_3_light
+  - model: appvoid/palmer-005-core
+    parameters:
+      weight: 0.14
+      density: 0.28
+
+```

config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 1024,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 1024,
+  "conv_use_xavier_init": true,
+  "dtype": "bfloat16",
+  "eos_token_id": 7,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 6656,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 7,
+  "pad_token_id": 0,
+  "transformers_version": "5.5.3"
+}

mergekit_config.yml

@@ -0,0 +1,26 @@
+merge_method: dare_ties
+base_model: MihaiPopa-1/LFM2.5-350M-heretic
+dtype: bfloat16
+
+parameters:
+  normalize: false
+  int8_mask: true
+
+models:
+  # slot_1_strongest
+  - model: mkurman/LiquidAI-LFM2.5-350M-SYNTH
+    parameters:
+      weight: 0.28
+      density: 0.38
+
+  # slot_2_medium
+  - model: squ11z1/claude-oss-350m
+    parameters:
+      weight: 0.22
+      density: 0.34
+
+  # slot_3_light
+  - model: appvoid/palmer-005-core
+    parameters:
+      weight: 0.14
+      density: 0.28

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8e653c9609494a944e36c3939cdf2cd46d28fdfcd348ae0bb8f02729b341c2f
+size 708984464

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}