Upload folder using huggingface_hub

README.md

@@ -2,28 +2,10 @@
 license: llama2
 ---
 
-These are exl2 quants of [Goliath-longLORA-120b-rope8-32k-fp16](https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-fp16).  
+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).
 
-Main branch includes `measurement.json` files for the new default dataset and the one used by [goliath-120b-exl2-rpcal](https://huggingface.co/Panchovix/goliath-120b-exl2-rpcal).
+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
-[2.65bpw](https://huggingface.co/aikitoria/Goliath-longLORA-120b-rope8-32k-exl2/tree/2.65bpw) 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).
 
-
-# Memory usage tests
-
-### 2.65bpw
-context 16k, cache 16: 46.9GiB (fits in 2x 3090)  
-context 32k, cache 8: 47GiB (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 not good either.  
-The 4.35bpw version is worse than normal goliath but better than goliath with rope scale applied for long context.  
-The version using the PIPPA dataset produces worse results than the one using the default dataset on any context length.
+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-4.35bpw-exl2-rpcal",
+  "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-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d820d9c79510e53403c504ae1e3f287be62a7492acf7e0bc0b30710432c82e9
+size 8540164670

output-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb6edd32be5873a86384c8899dc86074f6e2adfc320004debb0ee04d6b5ed38
+size 8577683146

output-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a777de894cd1fecc3083925ff62841a3ac82e0087b51e1b128f184b14f4e10d
+size 8586901052

output-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f95882dc642f7301dee530a9d4b64612b982aaf965ee2acc9c790da7ef166a3
+size 8562986136

output-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97fc0cf4a09431d8b1dd95c66fafe2330fc8e047625e3ef471bd2789837d3ba0
+size 8587774632

output-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd04cfe0a98f09d7684f4c6e5ae0d2a98bd9343ab15c204f9951200d8a082be
+size 8486402280

output-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089c536cce0b33edac0595c585f970680295ccb19a882898162fc8e3285831ee
+size 8587320272

output-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2ed6252eb70db95b90ae23cc2b5f0ae653cb3a00dd4bf7150482067f0710a9
+size 4587118672

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
+}