Upload folder using huggingface_hub

README.md

@@ -1,37 +1,13 @@
 ---
 license: llama2
-pipeline_tag: text-generation
 ---
 
-These are exl2 quants of [Goliath-longLORA-120b-rope8-32k-fp16](https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-fp16) which combines goliath with 32k context.  
+This is an interleaved merge of [Xwin-longLORA-70b-rope8-32k-fp16](https://huggingface.co/grimulkan/Xwin-longLORA-70b-rope8-32k-fp16) and [Euryale-1.3-longLORA-70b-rope8-32k-fp16](https://huggingface.co/grimulkan/Euryale-1.3-longLORA-70b-rope8-32k-fp16), using the same merge formula as alpindale's [goliath-120b](https://huggingface.co/alpindale/goliath-120b).
 
-I did not create that model, only discovered it and wanted to try it for myself, so I made smaller quants.  
+There is no additional fine-tuning. The resulting model seems to not be broken... you can test whether it is truly the original model + 32K capability (use linear rope scaling 8).
 
-# Available versions
-[main](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2/tree/main) has measurements for default dataset and the one for [goliath-120b-exl2-rpcal](https://huggingface.co/Panchovix/goliath-120b-exl2-rpcal)  
+[ChuckMcSneed](https://huggingface.co/ChuckMcSneed) did a benchmark [here](https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-fp16/discussions/1), indicating 30% degradation with 8x the context length.
 
-[2.65bpw](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2/tree/2.65bpw) using default dataset  
-[3bpw](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2/tree/3bpw) using default dataset  
-[4.35bpw](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2/tree/4.35bpw) using default dataset  
-[4.35bpw-rpcal](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2/tree/4.35bpw-rpcal) using PIPPA dataset
+A 6-bit EXL2 quantization is available [here](https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-2k-6bpw_h8_exl2). More EXL2 quants [here](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2), thanks to aikitoria.
 
-
-# Memory usage tests
-### 2.65bpw
-context 16k, cache 16: 46.9GiB (fits in 2x 3090)  
-context 32k, cache 8: 47GiB (fits in 2x 3090)  
-### 3bpw
-context 8k, cache 16: 47.4GiB (fits in 2x 3090)  
-context 16k, cache 8: 47.4GiB (fits in 2x 3090)  
-### 4.35bpw
-context 16k, cache 16: 70.1GiB (fits in 3x 3090)  
-context 32k, cache 8: 70.3GiB (fits in 3x 3090)  
-context 32k, cache 16: 78.7GiB (fits in A100 80GB)  
-
-# Super epic scientific test results
-- The 2.65bpw version suffered greatly, it's not completely broken, but it's no good either.  
-- The 3bpw version hasn't suffered as much, it's much more usable than the 2.65bpw one.  
-- The 4.35bpw version is a bit worse than normal 4k goliath but better than goliath with rope scale applied for 8k+ context.  
-- The version using the PIPPA dataset produces worse results than the one using the default dataset on any context length.
-
-My current strategy is to use the original goliath until its context is full and then switch over to this one.
+See [this discussion](https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16/discussions/2) for how the original 70B merges were created with longLORA.

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Goliath-longLORA-120b-rope8-32k-4bpw-exl2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 137,
+  "num_key_value_heads": 8,
+  "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": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

output-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2886dd745e7f5d48c86ee1a1dda2d03b48d1e81e7a0d7a1b42a0be687fd68e
+size 8555687884

output-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd040750fd62aafff40592e8277d3ce7f5b1999e5c26e046f3f87310c89458a
+size 8590012700

output-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8147ae501176a6d825f8457ceb8ad09d556abddeecfbe1f7540e178af508903
+size 8473090960

output-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61db69db7539de531a75835b14751db9cfd931e9bef8b42f285daf7365500bb
+size 8584011752

output-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3116b826c48f465d43ade9277ef67bd1b81a78ad811ddd0fae7abcb442099b46
+size 8573067184

output-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5b39612df45234a959f4b4058eb1d76aa7041a7ad10450b24e3a34207d2f21
+size 8585966968

output-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f205a654523862f76d92d6dc11adeb6183ee0d12b471860375e2a8cc81421bb
+size 8022507064

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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 +1,47 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}