metadata

license: other
license_name: writer-open-model-license
license_link: https://writer.com/legal/open-model-license/
pipeline_tag: text-generation
base_model: Writer/Palmyra-Med-70B-32K
model_creator: InternLM
model_name: Palmyra-Med-70B-32K
quantized_by: Second State Inc.
language:
  - en

Palmyra-Med-70B-32K-GGUF

Original Model

Writer/Palmyra-Med-70B-32K

Run with LlamaEdge

LlamaEdge version: v0.13.1 and above

Prompt template

Prompt type: llama-3-chat

Prompt string

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Context size: 32000

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Palmyra-Med-70B-32K-Q5_K_M.gguf \
    llama-api-server.wasm \
    --prompt-template llama-3-chat \
    --ctx-size 32000 \
    --model-name Palmyra-Med-70B-32K

Run as LlamaEdge command app

wasmedge --dir .:. \
  --nn-preload default:GGML:AUTO:Palmyra-Med-70B-32K-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template llama-3-chat \
  --ctx-size 32000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Palmyra-Med-70B-32K-Q2_K.gguf	Q2_K	2	26.4 GB	smallest, significant quality loss - not recommended for most purposes
Palmyra-Med-70B-32K-Q3_K_L.gguf	Q3_K_L	3	37.1 GB	small, substantial quality loss
Palmyra-Med-70B-32K-Q3_K_M.gguf	Q3_K_M	3	34.3 GB	very small, high quality loss
Palmyra-Med-70B-32K-Q3_K_S.gguf	Q3_K_S	3	30.9 GB	very small, high quality loss
Palmyra-Med-70B-32K-Q4_0.gguf	Q4_0	4	40.0 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Palmyra-Med-70B-32K-Q4_K_M.gguf	Q4_K_M	4	42.5 GB	medium, balanced quality - recommended
Palmyra-Med-70B-32K-Q4_K_S.gguf	Q4_K_S	4	40.3 GB	small, greater quality loss
Palmyra-Med-70B-32K-Q5_0.gguf	Q5_0	5	48.7 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Palmyra-Med-70B-32K-Q5_K_M.gguf	Q5_K_M	5	49.9 GB	large, very low quality loss - recommended
Palmyra-Med-70B-32K-Q5_K_S.gguf	Q5_K_S	5	48.7 GB	large, low quality loss - recommended
Palmyra-Med-70B-32K-Q6_K-00001-of-00002.gguf	Q6_K	6	29.8 GB	very large, extremely low quality loss
Palmyra-Med-70B-32K-Q6_K-00002-of-00002.gguf	Q6_K	6	28.0 GB	very large, extremely low quality loss
Palmyra-Med-70B-32K-Q8_0-00001-of-00003.gguf	Q8_0	8	29.8 GB	very large, extremely low quality loss - not recommended
Palmyra-Med-70B-32K-Q8_0-00002-of-00003.gguf	Q8_0	8	29.8 GB	very large, extremely low quality loss - not recommended
Palmyra-Med-70B-32K-Q8_0-00003-of-00003.gguf	Q8_0	8	15.4 GB	very large, extremely low quality loss - not recommended
Palmyra-Med-70B-32K-f16-00001-of-00005.gguf	f16	16	30.0 GB
Palmyra-Med-70B-32K-f16-00002-of-00005.gguf	f16	16	29.6 GB
Palmyra-Med-70B-32K-f16-00003-of-00005.gguf	f16	16	29.9 GB
Palmyra-Med-70B-32K-f16-00004-of-00005.gguf	f16	16	29.6 GB
Palmyra-Med-70B-32K-f16-00005-of-00005.gguf	f16	16	22.2 GB

Quantized with llama.cpp b3499