Upload folder using huggingface_hub

README.md

@@ -0,0 +1,51 @@
+---
+base_model:
+- codellama/CodeLlama-7b-Python-hf
+- tokyotech-llm/Swallow-7b-instruct-hf
+tags:
+- mergekit
+- merge
+
+---
+# merged-output
+
+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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [tokyotech-llm/Swallow-7b-instruct-hf](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+models:
+  - model: tokyotech-llm/Swallow-7b-instruct-hf
+    # no parameters necessary for base model
+  - model: codellama/CodeLlama-7b-Python-hf # follow user intent 
+    parameters:
+      density: 1
+      weight:
+      - filter: mlp.down_proj
+        value: [0.3, 0.25, 0.25, 0.15, 0.1]
+      - filter: mlp.gate_proj
+        value: [0.7, 0.25, 0.5, 0.45, 0.4]
+      - filter: mlp.up_proj
+        value: [0.7, 0.25, 0.5, 0.45, 0.4]
+      - filter: self_attn
+        value: [0.7, 0.25, 0.5, 0.45, 0.4]
+      - value: 0 # fallback for rest of tensors.
+merge_method: dare_ties
+base_model: tokyotech-llm/Swallow-7b-instruct-hf
+dtype: bfloat16
+tokenizer_source: union
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "tokyotech-llm/Swallow-7b-instruct-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "max_sequence_length": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 43176
+}

mergekit_config.yml

@@ -0,0 +1,21 @@
+
+models:
+  - model: tokyotech-llm/Swallow-7b-instruct-hf
+    # no parameters necessary for base model
+  - model: codellama/CodeLlama-7b-Python-hf # follow user intent 
+    parameters:
+      density: 1
+      weight:
+      - filter: mlp.down_proj
+        value: [0.3, 0.25, 0.25, 0.15, 0.1]
+      - filter: mlp.gate_proj
+        value: [0.7, 0.25, 0.5, 0.45, 0.4]
+      - filter: mlp.up_proj
+        value: [0.7, 0.25, 0.5, 0.45, 0.4]
+      - filter: self_attn
+        value: [0.7, 0.25, 0.5, 0.45, 0.4]
+      - value: 0 # fallback for rest of tensors.
+merge_method: dare_ties
+base_model: tokyotech-llm/Swallow-7b-instruct-hf
+dtype: bfloat16
+tokenizer_source: union

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e74f98221d12465b29964088ee8af1c04d4d02704b77c892dc5247d52be382
+size 1972768968

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b8cf2c556fe0086248ac890e0948fefca90ee14daed1994c9cf88411c1ac8cb
+size 1933652832

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de643128199c358548c262fdc437650a033c4074a76de679707d9ca0a7ed496e
+size 1979806576

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136aba7530f47e46c5cd71487c99496b1603afa5f61ed1d573bb6795d321b113
+size 1933652880

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8c37e8d4ea6e3cdfb6f8e6d6d83ce6f7bd60f57d07cf7fdc357dff4a1c9e40
+size 1967207432

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ece7cc8eee86f906579ac6519250a09577f72b5be392cf2a9aa3adc2cf0b7b
+size 1939222728

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7122fb06b1adcda8ef50041ec9ff1de68585f8e1ea7fb616c6ab4235c4148698
+size 1933661176

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "lm_head.weight": "model-00006-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}