Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model:
+- coldint/10.5B_v1
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# BestLlamaSN29
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [coldint/10.5B_v1](https://huggingface.co/coldint/10.5B_v1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: coldint/10.5B_v1
+        layer_range: [0, 36]
+  - sources: # add middle layers with residuals scaled to zero
+      - model: coldint/10.5B_v1
+        layer_range: [34, 36]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+              # - sources: # add middle layers with residuals scaled to zero
+              #- model: upstage/SOLAR-10.7B-v1.0
+              # layer_range: [14, 24]
+              # parameters:    
+              #scale:
+              #- filter: o_proj
+              #value: 0.0
+              # - filter: down_proj
+              # value: 0.0
+              # - value: 1.0
+  - sources:
+      - model: coldint/10.5B_v1
+        layer_range: [36, 43]
+merge_method: passthrough
+dtype: bfloat16
+
+
+
+
+
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "coldint/10.5B_v1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "device": "cuda:0",
+  "dtype": "bfloat16",
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14208,
+  "leave_empty": true,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 45,
+  "num_key_value_heads": 8,
+  "pop_states_at_layer": null,
+  "pretraining_tp": 1,
+  "return_states_at_layer": null,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "start_at_layer": null,
+  "stash_states_at_layer": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 96000
+}

mergekit_config.yml

@@ -0,0 +1,33 @@
+slices:
+  - sources:
+      - model: coldint/10.5B_v1
+        layer_range: [0, 36]
+  - sources: # add middle layers with residuals scaled to zero
+      - model: coldint/10.5B_v1
+        layer_range: [34, 36]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+              # - sources: # add middle layers with residuals scaled to zero
+              #- model: upstage/SOLAR-10.7B-v1.0
+              # layer_range: [14, 24]
+              # parameters:    
+              #scale:
+              #- filter: o_proj
+              #value: 0.0
+              # - filter: down_proj
+              # value: 0.0
+              # - value: 1.0
+  - sources:
+      - model: coldint/10.5B_v1
+        layer_range: [36, 43]
+merge_method: passthrough
+dtype: bfloat16
+
+
+
+

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cce1d8058c2c38c5526b18f9591c68d52f37464668a710f985f2d388096cf6
+size 9917771696

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a1b2220cc05edda36757858fe6420159768bd872ddb79e10d2359f911356dc
+size 9960824384

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cdcd3cca8331cb0c07d24da9b0f49ac6787e62d24d8d2b6849c7d9b9ae06c0f
+size 1182845864

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 21061394432}, "weight_map": {"lm_head.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,68 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "95993": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95994": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95995": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95996": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95997": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95998": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95999": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}