Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+f16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+base_model:
+- senseable/WestLake-7B-v2
+- internistai/base-7b-v0.2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged
+
+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 task_swapping merge method using [internistai/base-7b-v0.2](https://huggingface.co/internistai/base-7b-v0.2) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [senseable/WestLake-7B-v2](https://huggingface.co/senseable/WestLake-7B-v2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: internistai/base-7b-v0.2
+dtype: bfloat16
+merge_method: task_swapping
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model: senseable/WestLake-7B-v2
+    parameters:
+      diagonal_offset: 2.0
+      weight: 1.0
+  - layer_range: [0, 32]
+    model: internistai/base-7b-v0.2
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "internistai/base-7b-v0.2",
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47d078f5a294fc2ca82a318cd35b76f396daf32decdd85e5ccea6784caebd15
+size 14484732384

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0.dev0"
+}

mergekit_config.yml

@@ -0,0 +1,12 @@
+base_model: internistai/base-7b-v0.2
+dtype: bfloat16
+merge_method: task_swapping
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model: senseable/WestLake-7B-v2
+    parameters:
+      diagonal_offset: 2.0
+      weight: 1.0
+  - layer_range: [0, 32]
+    model: internistai/base-7b-v0.2

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38853d0e4b67c8f4a2b4f3e0e44567e57a765e13e20b1ecc9946cc3ae3605c5b
+size 1396746600

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f1ff4c149053820614272b9d7080ce5a2da838da62d3fc2019323aa254d64b
+size 1308675152

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d4bf144ebf3d59d62bb27c1d0df9d46d3a3cc08840c372e32241f91860c72f
+size 1308675152

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562ad48b9664d397f50cfe6de2799383d302a8e7850e78f82b46fec02b4eac2c
+size 1308675152

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fc5443f2a26970b0d4d8eb5e5d1ec32ec03ede6eec1f3bf99b72c4d448d78a
+size 1308675144

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f54760bc4914b9d6695228b964def32d24b4945ed9dda7988ba8a24e5f7e69
+size 1308675152

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8708f108b6216c56adc0c666a067456bf9fab97c8918139e449a74c3e4308c4
+size 1308675152

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb096916d9fc1a625cbc1c87b97b7452d97d2ce734d9b7a4ced6d0671a0177a
+size 1308675152

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc0ffa4a02796c3b28c9bf84fb566b7619a8e29597b84aee47be3df19d74ff3
+size 1308675144

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1e40e5b845f1187d0ad15da24378032cc520b138b7d0252e6f10a1f3389a17a
+size 1308675120

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30497ccea01c9e8c27c3a91caf945ac7ee2c5fb2148eaf8199fbfe8c992461a3
+size 1308675104

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": "{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{%- if not ns.found -%}{{- '### System:\n' + 'You are a medical assistant, provide accurate and unbiased answers to the questions.' + '\n\n' -}}{%- endif %}{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '### System:\n' + message['content'] + '\n\n' -}}{%- else -%}{%- if message['role'] == 'user' -%}{{-'### Instruction:\n' + message['content'] + '\n\n'-}}{%- else -%}{{-'### Response:\n' + message['content'] + '\n\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'### Response:\n'-}}{%- endif -%}",
+  "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",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}