Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- togethercomputer/LLaMA-2-7B-32K
+- Qwen/Qwen1.5-7B
+base_model:
+- togethercomputer/LLaMA-2-7B-32K
+- Qwen/Qwen1.5-7B
+---
+
+# llama-qwen
+
+llama-qwen is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [togethercomputer/LLaMA-2-7B-32K](https://huggingface.co/togethercomputer/LLaMA-2-7B-32K)
+* [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: togethercomputer/LLaMA-2-7B-32K
+        layer_range: [0, 20]
+      - model: Qwen/Qwen1.5-7B
+        layer_range: [0, 20]
+merge_method: slerp
+base_model: togethercomputer/LLaMA-2-7B-32K
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "ajay141/llama-qwen"
+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"])
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "togethercomputer/LLaMA-2-7B-32K",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModelForCausalLM": "togethercomputer/LLaMA-2-7B-32K--modeling_flash_llama.LlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 20,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: togethercomputer/LLaMA-2-7B-32K
+        layer_range: [0, 20]
+      - model: Qwen/Qwen1.5-7B
+        layer_range: [0, 20]
+merge_method: slerp
+base_model: togethercomputer/LLaMA-2-7B-32K
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d31271bb6ad874bba80c7d6126d78fb2b8d956c2e2548d31ac16efed1bc74f6c
+size 1933644528

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:759968947098d22138a8cea29af77d55f469ad9c04b7acc713a0eff43b93d68d
+size 1971384520

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8a1797d3c495c23e8ed0104674c5550df27421c646fb1e10df47f67f3faee3
+size 1933652872

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54ff1a22897bb331807cd7877f829bab54a3450d8689b2071e733649b39eeb4
+size 1933677768

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ca9763e1d969f9bd9cc63c88e8f1ef76823536fd8bb765f79129a6226c600d
+size 847292072

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1", "total_size": 8619630592}, "weight_map": {"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.embed_tokens.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00005.safetensors", "lm_head.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,42 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}