Upload folder using huggingface_hub

README.md

@@ -1,24 +1,33 @@
 ---
-tags:
-- merge
-- mergekit
-- lazymergekit
-- codellama/CodeLlama-34b-Instruct-hf
-- Phind/Phind-CodeLlama-34B-v2
 base_model:
 - codellama/CodeLlama-34b-Instruct-hf
 - Phind/Phind-CodeLlama-34B-v2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# merge-legacy
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
 
-# uptimeai-8273
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) as a base.
 
-uptimeai-8273 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
-* [codellama/CodeLlama-34b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf)
+### Models Merged
+
+The following models were included in the merge:
 * [Phind/Phind-CodeLlama-34B-v2](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2)
 
-## 🧩 Configuration
+### Configuration
+
+The following YAML configuration was used to produce this model:
 
 ```yaml
+
 models:
   - model: codellama/CodeLlama-34b-Instruct-hf
     parameters:
@@ -34,29 +43,5 @@ parameters:
   normalize: true
   int8_mask: true
 dtype: float16
-```
-
-## 💻 Usage
 
-```python
-!pip install -qU transformers accelerate
-
-from transformers import AutoTokenizer
-import transformers
-import torch
-
-model = "okeanos/uptimeai-8273"
-messages = [{"role": "user", "content": "What is a large language model?"}]
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    torch_dtype=torch.float16,
-    device_map="auto",
-)
-
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
-```
+```

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "codellama/CodeLlama-34b-Instruct-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+
+models:
+  - model: codellama/CodeLlama-34b-Instruct-hf
+    parameters:
+      density: [1, 0.7, 0.1] # density gradient
+      weight: 1.0
+  - model: Phind/Phind-CodeLlama-34B-v2
+    parameters:
+      density: 0.5
+      weight: [0, 0.3, 0.7, 1] # weight gradient
+merge_method: dare_ties
+base_model: codellama/CodeLlama-34b-Instruct-hf
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a31a33b27a97e0f32e00aef3231dd310eb527e283f67679e83320a8519b36a
+size 9852623728

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c5f76cfc30bb6845de10f2aaafd0938c6ea38614b2c08ee7195b11882bdd072
+size 9689078904

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7bc6f29c83bc7822ff172d5e3f3358eee0f249198bf95a79bf6811ef479485
+size 9689078928

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac14d7bd2066f1a3735761bc6a5b79d2e30d917b7109e95657b8cadba2f2ae4
+size 9689078928

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e91530a012985f3e97c1c1eb4c0f994045d80fb6b7a9e0a8ca56b4eb51945f8
+size 9689078928

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0fd6a5b34aeb57ba6797c3b9d1921541aaba7ce5e06ef3eb215af9afe85f16
+size 9689078928

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a542b4673c281f20d6c9786ec7e72c06b2b1f700fc42d607ce52fe76190633a
+size 9189972632

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.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.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.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.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.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.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.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-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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
+  },
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "32000": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}