TeeZee commited on
Commit
d56049b
1 Parent(s): c0ef5f3

Upload 10 files

Browse files
DarkForest-20B-v2.0.jpg ADDED
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: microsoft-research-license
4
+ tags:
5
+ - merge
6
+ - not-for-all-audiences
7
+ ---
8
+ # DarkForest 20B v2.0
9
+
10
+ ![image/png](https://huggingface.co/TeeZee/DarkForest-20B-v2.0/resolve/main/DarkForest-20B-v2.0.jpg)
11
+
12
+
13
+ ## Model Details
14
+
15
+ - To create this model two step procedure was used. First a new 20B model was created using [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b)
16
+ and [KoboldAI/LLaMA2-13B-Erebus-v3](https://huggingface.co/KoboldAI/LLaMA2-13B-Erebus-v3) , deatils of the merge in [darkforest_v2_step1.yml](https://huggingface.co/TeeZee/DarkForest-20B-v2.0/resolve/main/darkforest_v2_step1.yml)
17
+ - then [jebcarter/psyonic-cetacean-20B](https://huggingface.co/jebcarter/psyonic-cetacean-20B)
18
+ - and [TeeZee/BigMaid-20B-v1.0](https://huggingface.co/TeeZee/BigMaid-20B-v1.0) was used to produce the final model, merge config in [darkforest_v2_step2.yml](https://huggingface.co/TeeZee/DarkForest-20B-v2.0/resolve/main/darkforest_v2_step2.yml)
19
+ - The resulting model has approximately 20 billion parameters.
20
+
21
+
22
+ **Warning: This model can produce NSFW content!**
23
+
24
+ ## Results
25
+
26
+ - main difference to v1.0 - model has much better sense of humor.
27
+ - produces SFW nad NSFW content without issues, switches context seamlessly.
28
+ - good at following instructions.
29
+ - good at tracking multiple characters in one scene.
30
+ - very creative, scenarios produced are mature and complicated, model doesn't shy from writing about PTSD, menatal issues or complicated relationships.
31
+ - NSFW output is more creative and suprising than typical limaRP output.
32
+ - definitely for mature audiences, not only because of vivid NSFW content but also because of overall maturity of stories it produces.
33
+ - This is NOT Harry Potter level storytelling.
34
+
35
+ All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
36
+ <a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "F:\\merger\\mergekit\\again1_rev",
3
+ "antemplate": "[Genre: <|>]",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 13824,
15
+ "max_position_embeddings": 4096,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 40,
18
+ "num_hidden_layers": 62,
19
+ "num_key_value_heads": 40,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.35.2",
27
+ "use_cache": false,
28
+ "vocab_size": 32000,
29
+ "welcome": "## Warning: This model has a very heavy NSFW bias and is not suitable for use by minors!\n\nYou are currently running story-writing model `Erebus, version 3 (LLaMA2 13B).`\n\n This model is made by [Mr. Seeker](https://www.patreon.com/mrseeker) with help of ProudNoob and the KoboldAI team.\n\n### How to use this model\n\nErebus is designed to generate short stories and novels. Use the author's note to give it a certain genre to follow, use memory to give an overview of the story and use World Information to give specific details about the characters. To start off, give the AI an idea of what you are writing about by setting the scene. Give the AI around 10 sentences that make your story interesting to read. Introduce your character, describe the world, blow something up, or let the AI use its creative mind."
30
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.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.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.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.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.4.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.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.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.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.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.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.47.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.48.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.49.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.50.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "lm_head.weight": "model-00003-of-00005.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.51.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.52.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.53.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.54.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.55.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.56.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.57.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.58.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.59.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.60.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.61.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.safetensors"}}
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af925060c26b6e46846a6f75aefda4f7e83c08d345035c57cec08e7dd73a75f9
3
+ size 8571576648
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6a0a3eff23f67bd136f6cb98bde7d74d9a7e4b82f4d9453225b37d8c054b3a
3
+ size 3208099048
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
31
+ "legacy": false,
32
+ "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": null,
34
+ "padding_side": "right",
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }