Upload folder using huggingface_hub

4bits-128g-desc_act_False-damp_0.01/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "models/ludis_tsukasa-limarp-7b",
+  "architectures": [
+    "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "use_cache": false,
+  "vocab_size": 32003
+}

4bits-128g-desc_act_False-damp_0.01/gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa5b10f496042400b28197bf1c418b2584df8dad53220ce86d126b65ac2510d
+size 3896763880

4bits-128g-desc_act_False-damp_0.01/quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

4bits-128g-desc_act_True-damp_0.01/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "models/ludis_tsukasa-limarp-7b",
+  "architectures": [
+    "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "use_cache": false,
+  "vocab_size": 32003
+}

4bits-128g-desc_act_True-damp_0.01/gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087f416a10bbc22c5a96f2af0c52c80d611b75ecc0bc315c21d199ee44dacbf1
+size 3896763880

4bits-128g-desc_act_True-damp_0.01/quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

4bits-1g-desc_act_True-damp_0.01/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "models/ludis_tsukasa-limarp-7b",
+  "architectures": [
+    "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "use_cache": false,
+  "vocab_size": 32003
+}

4bits-1g-desc_act_True-damp_0.01/gptq_model-4bit-1g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9986581c0f3b0647722ba062323a8e4f3e0826041208008c0b882a3d021d173
+size 19960294808

4bits-1g-desc_act_True-damp_0.01/quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 1,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

4bits-32g-desc_act_True-damp_0.01/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "models/ludis_tsukasa-limarp-7b",
+  "architectures": [
+    "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "use_cache": false,
+  "vocab_size": 32003
+}

4bits-32g-desc_act_True-damp_0.01/gptq_model-4bit-32g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a69623c5f7ffdafd7dbb5e5b0c22faa28f73dfacdb933ce599b061d11a6189
+size 4276217776

4bits-32g-desc_act_True-damp_0.01/quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

4bits-64g-desc_act_True-damp_0.01/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "models/ludis_tsukasa-limarp-7b",
+  "architectures": [
+    "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.1",
+  "use_cache": false,
+  "vocab_size": 32003
+}

4bits-64g-desc_act_True-damp_0.01/gptq_model-4bit-64g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcecc5a00bcaa8bd2f0b058b3d141d82ab8ef2449b086c0a2b206e21b23407e
+size 4023248424

4bits-64g-desc_act_True-damp_0.01/quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 64,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

README.md

@@ -0,0 +1,32 @@
+---
+datasets:
+  - ewof/koishi-instruct-metharme
+  - PygmalionAI/PIPPA
+---
+
+## GPTQ
+
+gptq quants for ludis/tsukasa-limarp-7b download the original model except for the .bin files (or download everything and delete the .bin files) then move the contents from whichever quants folder you want to use into the original model folder and run with autogptq
+
+## Base Model
+
+native fine tune of ludis/tsukasa-7b
+
+## Prompting
+
+https://rentry.org/v43eo - reccomended prompts and gen settings
+
+The current model version has been trained on prompts using three different roles, which are denoted by the following tokens: `<|system|>`, `<|user|>` and `<|model|>`.
+
+The `<|system|>` prompt can be used to inject out-of-channel information behind the scenes, while the `<|user|>` prompt should be used to indicate user input. The `<|model|>` token should then be used to indicate that the model should generate a response. These tokens can happen multiple times and be chained up to form a conversation history.
+
+## Benchmarks
+
+trained on commit de693ac of the koishi dataset for 1 epoch as apart of 
+
+trained on commit 36fc235 of pippa metharme for 1 epoch as apart of 
+
+trained on Version 2023-09-03 of LimaRP (without ponyville, lolicit, all the fallen, and eka's portal subsets) for 2 epochs
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f38f3a89203d118da8b477/lvXgfxrb5v4ceEtZfVrYP.png)
+