Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+base_model:
+- HuggingFaceH4/zephyr-7b-beta
+- meta-llama/Llama-2-7b-chat-hf
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# zephyr-llama2-7b-ties
+
+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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: HuggingFaceH4/zephyr-7b-beta
+  - model: meta-llama/Llama-2-7b-chat-hf
+    parameters:
+        density: 0.1
+        weight:   # weight gradient
+        - filter: mlp
+          value: 0.1
+        - value: 0
+merge_method: ties
+base_model: HuggingFaceH4/zephyr-7b-beta
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,15 @@
+models:
+  - model: HuggingFaceH4/zephyr-7b-beta
+  - model: meta-llama/Llama-2-7b-chat-hf
+    parameters:
+        density: 0.1
+        weight:   # weight gradient
+        - filter: mlp
+          value: 0.1
+        - value: 0
+merge_method: ties
+base_model: HuggingFaceH4/zephyr-7b-beta
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79427b33da9c9b27e58aed99ad1199db7cb0f5866246754918e0707faa57aef6
+size 1973473552

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543a8ed7b3b0305f64d310d0f0577569b8d447fb18eccefc44ea8cd9a30423e4
+size 1979798000

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf98e26a5ff25efcc74616d821a1d460b057c541cfc215ace882b6b1f3dfa8a
+size 1946227312

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a74754307c20982c3527d9eec4340b9cce9b2a815e7d789790cf21849d4b962f
+size 1979798016

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b37484df470231e440fb0e5bebd2c06522c2c02952f3f28f81fa7f395c37cf
+size 1946227336

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6db1ef117c2dd23effe1f5d102ea9ad0a81798324f0fc810660e808bb79930
+size 1979798016

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4b8aa5c55eefe797717164a30dbcc929c273e3a1a973b1baaadc2e98caa73d
+size 1862340784

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bace085db69830452ffeaf7d1fc22b0f6ca84536b31976c4f0829c1fe8fee102
+size 815834664

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "lm_head.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

ties.yml

@@ -0,0 +1,15 @@
+models:
+  - model: HuggingFaceH4/zephyr-7b-beta
+  - model: meta-llama/Llama-2-7b-chat-hf
+    parameters:
+        density: 0.1
+        weight:   # weight gradient
+        - filter: mlp
+          value: 0.1
+        - value: 0
+merge_method: ties
+base_model: HuggingFaceH4/zephyr-7b-beta
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}