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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+base_model:
+- cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
+- trashpanda-org/MS-24B-Instruct-Mullein-v0
+- huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
+- PocketDoc/Dans-DangerousWinds-V1.1.1-24b
+- ReadyArt/Omega-Darker_The-Final-Directive-24B
+- Gryphe/Pantheon-RP-1.8-24b-Small-3.1
+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 [Karcher Mean](https://en.wikipedia.org/wiki/Karcher_mean) merge method using [Gryphe/Pantheon-RP-1.8-24b-Small-3.1](https://huggingface.co/Gryphe/Pantheon-RP-1.8-24b-Small-3.1) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition](https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition)
+* [trashpanda-org/MS-24B-Instruct-Mullein-v0](https://huggingface.co/trashpanda-org/MS-24B-Instruct-Mullein-v0)
+* [huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated](https://huggingface.co/huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated)
+* [PocketDoc/Dans-DangerousWinds-V1.1.1-24b](https://huggingface.co/PocketDoc/Dans-DangerousWinds-V1.1.1-24b)
+* [ReadyArt/Omega-Darker_The-Final-Directive-24B](https://huggingface.co/ReadyArt/Omega-Darker_The-Final-Directive-24B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
+  - model: trashpanda-org/MS-24B-Instruct-Mullein-v0
+  - model: PocketDoc/Dans-DangerousWinds-V1.1.1-24b
+  - model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
+  - model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
+  - model: ReadyArt/Omega-Darker_The-Final-Directive-24B
+merge_method: karcher
+base_model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
+parameters:
+  max_iter: 1000
+normalize: true
+int8_mask: true
+tokenizer_source: base
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 999,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,15 @@
+models:
+  - model: cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
+  - model: trashpanda-org/MS-24B-Instruct-Mullein-v0
+  - model: PocketDoc/Dans-DangerousWinds-V1.1.1-24b
+  - model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
+  - model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
+  - model: ReadyArt/Omega-Darker_The-Final-Directive-24B
+merge_method: karcher
+base_model: Gryphe/Pantheon-RP-1.8-24b-Small-3.1
+parameters:
+  max_iter: 1000
+normalize: true
+int8_mask: true
+tokenizer_source: base
+dtype: bfloat16

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbf9afe7c4eba5da9e54e16b102fcbe9bc052ae9240a67a92d6f8525b9f4a23
+size 4907389312

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c6b02598ddba7e6bf62accce2d0cb36419ef986cc447f9983f5e91691e73628
+size 4781592832

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b044da32243e06d98ddffed9fea3e4e16bc1b5611e84b4c5ca48348f5e10ea
+size 4781592816

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e85a77a60ea4ee697992d9f124b1bf2b56e1ffa3001821cef37895d4005312
+size 4886471592

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e4ab57ad0aee6f3158573a262d6a32a553218604d34c83d59be07cd13cbbd83
+size 4781592832

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f808e670105c89f18007eac5058d98a46bf8ab27bf2b1bd7827af2e7601d5341
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f476b09aac875a9b8d4c91208cd7c00fb6106b0090999aaa7ab8e89ff79993e2
+size 4886471592

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21666002ab6b44b9a7f4330696baeb1c2bd8b3c819d84e49017e55699dcae05
+size 4781592832

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92ecfc50f224e8e10b3e91de68cace2f51a0774746e8284013303364c43cf05
+size 4781592800

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f477b0a002dd0a6500c52419933928601cfb8420644cb12099eb8619ffc1577e
+size 3774959456

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e5daf1e619597fd56ff036925ea189916417c665d5bdd61b80199cf8d4e6d2
+size 17078029