Upload folder using huggingface_hub

README.md

@@ -0,0 +1,49 @@
+---
+base_model:
+- 152334H/miqu-1-70b-sf
+- Xwin-LM/Xwin-LM-70B-V0.1
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)
+* [Xwin-LM/Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [0, 32]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: 152334H/miqu-1-70b-sf
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "152334H/miqu-1-70b-sf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 32764,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: 152334H/miqu-1-70b-sf
+        layer_range: [0, 32]
+      - model: Xwin-LM/Xwin-LM-70B-V0.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: 152334H/miqu-1-70b-sf
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48678b1be413a8d6621ab386aa1401a7fe82acc7d65af4bc1ab8aaff789a64b
+size 9852607072

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cde20841853199163bde10ccbdda6a9ac07589b6a2f5da7782e49c8938f7fe
+size 9798079712

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0af03a1d3b2b93f17a5f027dc80fa25db17f899a805a5d0fab5dcdfc997dc85
+size 9630308664

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6154e53a425406baf0e5e8efda490992d53dbe691220ef2f314a064370afc710
+size 9831650920

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23e591cf65d20dd05f6dc1be5f1c615813e939163febf25483b1c6cf123744a
+size 9932281808

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094df714c898fea635fd7788e19a4db7efbde5318256a2e6ecca112f41bca66f
+size 6765579776

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}