Add common model files

README.md

@@ -43,7 +43,7 @@ convert.py -i ${MODEL_DIR_FP16} -o ${WIP_DIR} -cf ${MODEL_DIR_EXL} -c ${CALIBRAT
 
 ### Perplexity
 
-Perplexity was measured with the [test_inference.py](https://github.com/turboderp/exllamav2/blob/master/test_inference.py) script:
+Perplexity was measured with [test_inference.py](https://github.com/turboderp/exllamav2/blob/master/test_inference.py) script:
 ```
 test_inference.py -m ${MODEL_DIR_EXL} -ed ${PPL_DATASET}
 ```
@@ -53,14 +53,14 @@ test_inference.py -m ${MODEL_DIR_EXL} -ed ${PPL_DATASET}
 For the point of reference, Phind says that the original model achieves **73.8** Human-Eval score.
 
 Unfortunately, FP16/INT8 weights of this model won't fit on my RTX 4090, but FP16 quantized to NF4 fits,
-so I generated samples with [this](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/tf.human-eval.py) script:
+so I generated samples with [tf.human-eval.py](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/tf.human-eval.py) script:
 ```
 python tf.human-eval.py -m ${MODEL_DIR_FP16} -o nf4-samples.jsonl
 ```
 
 NF4 variant gives us **0.70731707**
 
-Samples for the Human-Eval scores of EXL2 quants were generated with [this](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/exl2.human-eval.py)
+Samples for the Human-Eval scores of EXL2 quants were generated with [exl2.human-eval.py](https://github.com/epicfilemcnulty/llm-tools/blob/main/eval/exl2.human-eval.py)
 script like this:
 ```
 python exl2.human-eval.py -m ${MODEL_DIR_EXL2} -c 4096 ${BPW}-samples.jsonl

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/fsx/Phind-CodeLlama-34B-v1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.33.0.dev0"
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,37 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}